Search Results for author:
Found 155 papers, 55 papers with code
Social-MAE: Social Masked Autoencoder for Multi-person Motion Representation Learning
The framework uses masked modeling to pre-train the encoder to reconstruct masked human joint trajectories, enabling it to learn generalizable and data efficient representations of motion in human crowded scenes.
JRDB-PanoTrack: An Open-world Panoptic Segmentation and Tracking Robotic Dataset in Crowded Human Environments
JRDB-PanoTrack includes (1) various data involving indoor and outdoor crowded scenes, as well as comprehensive 2D and 3D synchronized data modalities; (2) high-quality 2D spatial panoptic segmentation and temporal tracking annotations, with additional 3D label projections for further spatial understanding; (3) diverse object classes for closed- and open-world recognition benchmarks, with OSPA-based metrics for evaluation.
PoIFusion: Multi-Modal 3D Object Detection via Fusion at Points of Interest
In this work, we present PoIFusion, a simple yet effective multi-modal 3D object detection framework to fuse the information of RGB images and LiDAR point clouds at the point of interest (abbreviated as PoI).
GaussCtrl: Multi-View Consistent Text-Driven 3D Gaussian Splatting Editing
We propose GaussCtrl, a text-driven method to edit a 3D scene reconstructed by the 3D Gaussian Splatting (3DGS).
Motion Mamba: Efficient and Long Sequence Motion Generation with Hierarchical and Bidirectional Selective SSM
Human motion generation stands as a significant pursuit in generative computer vision, while achieving long-sequence and efficient motion generation remains challenging.
Symmetry-Breaking Augmentations for Ad Hoc Teamwork
In many collaborative settings, artificial intelligence (AI) agents must be able to adapt to new teammates that use unknown or previously unobserved strategies.
Few and Fewer: Learning Better from Few Examples Using Fewer Base Classes
Fine-tuning is ineffective for few-shot learning, since the target dataset contains only a handful of examples.
SayPlan: Grounding Large Language Models using 3D Scene Graphs for Scalable Robot Task Planning
To ensure the scalability of our approach, we: (1) exploit the hierarchical nature of 3DSGs to allow LLMs to conduct a 'semantic search' for task-relevant subgraphs from a smaller, collapsed representation of the full graph; (2) reduce the planning horizon for the LLM by integrating a classical path planner and (3) introduce an 'iterative replanning' pipeline that refines the initial plan using feedback from a scene graph simulator, correcting infeasible actions and avoiding planning failures.
Semantic Segmentation on 3D Point Clouds with High Density Variations
LiDAR scanning for surveying applications acquire measurements over wide areas and long distances, which produces large-scale 3D point clouds with significant local density variations.
Assessing Domain Gap for Continual Domain Adaptation in Object Detection
To ensure reliable object detection in autonomous systems, the detector must be able to adapt to changes in appearance caused by environmental factors such as time of day, weather, and seasons.
Residual Pattern Learning for Pixel-wise Out-of-Distribution Detection in Semantic Segmentation
Semantic segmentation models classify pixels into a set of known (``in-distribution'') visual classes.
Ranked #1 on
Anomaly Detection
on Fishyscapes
(using extra training data)
Predicting Topological Maps for Visual Navigation in Unexplored Environments
We propose a robotic learning system for autonomous exploration and navigation in unexplored environments.
ActiveRMAP: Radiance Field for Active Mapping And Planning
We, for the first time, present an RGB-only active vision framework using radiance field representation for active 3D reconstruction and planning in an online manner.
What Images are More Memorable to Machines?
This paper studies the problem of measuring and predicting how memorable an image is to pattern recognition machines, as a path to explore machine intelligence.
SC-DepthV3: Robust Self-supervised Monocular Depth Estimation for Dynamic Scenes
Self-supervised monocular depth estimation has shown impressive results in static scenes.
Indoor Monocular Depth Estimation
Monocular Depth Estimation
+1
Globally Optimal Event-Based Divergence Estimation for Ventral Landing
This is achieved by estimating divergence (inverse TTC), which is the rate of radial optic flow, from the event stream generated during landing.
The Edge of Disaster: A Battle Between Autonomous Racing and Safety
Autonomous racing represents a uniquely challenging control environment where agents must act while on the limits of a vehicle's capability in order to set competitive lap times.
CropMix: Sampling a Rich Input Distribution via Multi-Scale Cropping
We present a simple method, CropMix, for the purpose of producing a rich input distribution from the original dataset distribution.
Asynchronous Optimisation for Event-based Visual Odometry
Event cameras open up new possibilities for robotic perception due to their low latency and high dynamic range.
You Only Cut Once: Boosting Data Augmentation with a Single Cut
We present You Only Cut Once (YOCO) for performing data augmentations.
PropMix: Hard Sample Filtering and Proportional MixUp for Learning with Noisy Labels
The most competitive noisy label learning methods rely on an unsupervised classification of clean and noisy samples, where samples classified as noisy are re-labelled and "MixMatched" with the clean samples.
Ranked #1 on
Image Classification with Label Noise
on CIFAR-100
Image Classification with Label Noise
Learning with noisy labels
Weakly Supervised Training of Monocular 3D Object Detectors Using Wide Baseline Multi-view Traffic Camera Data
Our method achieves vehicle 7DoF pose prediction accuracy on our dataset comparable to the top performing monocular 3D object detectors on autonomous vehicle datasets.
Autonomy and Perception for Space Mining
Future Moon bases will likely be constructed using resources mined from the surface of the Moon.
ODAM: Object Detection, Association, and Mapping using Posed RGB Video
Localizing objects and estimating their extent in 3D is an important step towards high-level 3D scene understanding, which has many applications in Augmented Reality and Robotics.
JRDB-Act: A Large-scale Dataset for Spatio-temporal Action, Social Group and Activity Detection
However, learning to recognise human actions and their social interactions in an unconstrained real-world environment comprising numerous people, with potentially highly unbalanced and long-tailed distributed action labels from a stream of sensory data captured from a mobile robot platform remains a significant challenge, not least owing to the lack of a reflective large-scale dataset.
Unsupervised Scale-consistent Depth Learning from Video
We propose a monocular depth estimator SC-Depth, which requires only unlabelled videos for training and enables the scale-consistent prediction at inference time.
TRiPOD: Human Trajectory and Pose Dynamics Forecasting in the Wild
Joint forecasting of human trajectory and pose dynamics is a fundamental building block of various applications ranging from robotics and autonomous driving to surveillance systems.
Looking Beyond Two Frames: End-to-End Multi-Object Tracking Using Spatial and Temporal Transformers
Tracking a time-varying indefinite number of objects in a video sequence over time remains a challenge despite recent advances in the field.
ScanMix: Learning from Severe Label Noise via Semantic Clustering and Semi-Supervised Learning
We propose a new training algorithm, ScanMix, that explores semantic clustering and semi-supervised learning (SSL) to allow superior robustness to severe label noise and competitive robustness to non-severe label noise problems, in comparison to the state of the art (SOTA) methods.
Ranked #24 on
Image Classification
on mini WebVision 1.0
Rotation Coordinate Descent for Fast Globally Optimal Rotation Averaging
Under mild conditions on the noise level of the measurements, rotation averaging satisfies strong duality, which enables global solutions to be obtained via semidefinite programming (SDP) relaxation.
LongReMix: Robust Learning with High Confidence Samples in a Noisy Label Environment
Deep neural network models are robust to a limited amount of label noise, but their ability to memorise noisy labels in high noise rate problems is still an open issue.
Ranked #4 on
Image Classification
on Food-101N
Self-supervised Mean Teacher for Semi-supervised Chest X-ray Classification
In this paper, we propose Self-supervised Mean Teacher for Semi-supervised (S$^2$MTS$^2$) learning that combines self-supervised mean-teacher pre-training with semi-supervised fine-tuning.
DF-VO: What Should Be Learnt for Visual Odometry?
More surprisingly, they show that the well-trained networks enable scale-consistent predictions over long videos, while the accuracy is still inferior to traditional methods because of ignoring geometric information.
Semantics for Robotic Mapping, Perception and Interaction: A Survey
In robotics and related research fields, the study of understanding is often referred to as semantics, which dictates what does the world "mean" to a robot, and is strongly tied to the question of how to represent that meaning.
MOLTR: Multiple Object Localisation, Tracking, and Reconstruction from Monocular RGB Videos
Given a new RGB frame, MOLTR firstly applies a monocular 3D detector to localise objects of interest and extract their shape codes that represent the object shapes in a learned embedding space.
EvidentialMix: Learning with Combined Open-set and Closed-set Noisy Labels
In this work, we study a new variant of the noisy label problem that combines the open-set and closed-set noisy labels, and introduce a benchmark evaluation to assess the performance of training algorithms under this setup.
HM4: Hidden Markov Model with Memory Management for Visual Place Recognition
However, this creates an unboundedly-growing database that poses time and memory scalability challenges for place recognition methods.
MOTChallenge: A Benchmark for Single-Camera Multiple Target Tracking
We present MOTChallenge, a benchmark for single-camera Multiple Object Tracking (MOT) launched in late 2014, to collect existing and new data, and create a framework for the standardized evaluation of multiple object tracking methods.
How Trustworthy are Performance Evaluations for Basic Vision Tasks?
This paper examines performance evaluation criteria for basic vision tasks involving sets of objects namely, object detection, instance-level segmentation and multi-object tracking.
Socially and Contextually Aware Human Motion and Pose Forecasting
In this paper, we propose a novel framework to tackle both tasks of human motion (or trajectory) and body skeleton pose forecasting in a unified end-to-end pipeline.
Joint Learning of Social Groups, Individuals Action and Sub-group Activities in Videos
In this paper, we solve the problem of simultaneously grouping people by their social interactions, predicting their individual actions and the social activity of each social group, which we call the social task.
Auto-Rectify Network for Unsupervised Indoor Depth Estimation
However, excellent results have mostly been obtained in street-scene driving scenarios, and such methods often fail in other settings, particularly indoor videos taken by handheld devices.
Ranked #62 on
Monocular Depth Estimation
on NYU-Depth V2
FroDO: From Detections to 3D Objects
We introduce FroDO, a method for accurate 3D reconstruction of object instances from RGB video that infers object location, pose and shape in a coarse-to-fine manner.
MOT20: A benchmark for multi object tracking in crowded scenes
The benchmark for Multiple Object Tracking, MOTChallenge, was launched with the goal to establish a standardized evaluation of multiple object tracking methods.
Multi-Object Tracking
Multiple Object Tracking with Transformer
+2
3D Gated Recurrent Fusion for Semantic Scene Completion
This paper tackles the problem of data fusion in the semantic scene completion (SSC) task, which can simultaneously deal with semantic labeling and scene completion.
Ranked #14 on
3D Semantic Scene Completion
on NYUv2
Hyperspectral Classification Based on 3D Asymmetric Inception Network with Data Fusion Transfer Learning
Hyperspectral image(HSI) classification has been improved with convolutional neural network(CNN) in very recent years.
Switchable Precision Neural Networks
Instantaneous and on demand accuracy-efficiency trade-off has been recently explored in the context of neural networks slimming.
Automatic Pruning for Quantized Neural Networks
In particular, for ResNet-18 on ImageNet, we prune 26. 12% of the model size with Binarized Neural Network quantization, achieving a top-1 classification accuracy of 47. 32% in a model of 2. 47 MB and 59. 30% with a 2-bit DoReFa-Net in 4. 36 MB.
Learn to Predict Sets Using Feed-Forward Neural Networks
In our formulation we define a likelihood for a set distribution represented by a) two discrete distributions defining the set cardinally and permutation variables, and b) a joint distribution over set elements with a fixed cardinality.
Depth Based Semantic Scene Completion with Position Importance Aware Loss
We propose PALNet, a novel hybrid network for SSC based on single depth.
SG-VAE: Scene Grammar Variational Autoencoder to generate new indoor scenes
Our method learns the co-occurrences, and appearance parameters such as shape and pose, for different objects categories through a grammar-based auto-encoder, resulting in a compact and accurate representation for scene layouts.
NeuRoRA: Neural Robust Rotation Averaging
Although the idea of replacing robust optimization methods by a graph-based network is demonstrated only for multiple rotation averaging, it could easily be extended to other graph-based geometric problems, for example, pose-graph optimization.
Improved Visual Localization via Graph Smoothing
One solution to this problem is to learn a deep neural network to infer the pose of a query image after learning on a dataset of images with known poses.
Meta Learning with Differentiable Closed-form Solver for Fast Video Object Segmentation
This paper tackles the problem of video object segmentation.
Structured Binary Neural Networks for Image Recognition
Experiments on both classification, semantic segmentation and object detection tasks demonstrate the superior performance of the proposed methods over various quantized networks in the literature.
Visual Odometry Revisited: What Should Be Learnt?
In this work we present a monocular visual odometry (VO) algorithm which leverages geometry-based methods and deep learning.
Unsupervised Scale-consistent Depth and Ego-motion Learning from Monocular Video
To the best of our knowledge, this is the first work to show that deep networks trained using unlabelled monocular videos can predict globally scale-consistent camera trajectories over a long video sequence.
Ranked #61 on
Monocular Depth Estimation
on KITTI Eigen split
An Evaluation of Feature Matchers for Fundamental Matrix Estimation
According to this, we propose three high-quality matching systems and a Coarse-to-Fine RANSAC estimator.
In defense of OSVOS
Through adding a common module, video loss, which we formulate with various forms of constraints (including weighted BCE loss, high-dimensional triplet loss, as well as a novel mixed instance-aware video loss), to train the parent network in the step (2), the network is then better prepared for the step (3), i. e. online fine-tuning on the target instance.
Effective Training of Convolutional Neural Networks with Low-bitwidth Weights and Activations
Furthermore, we propose a second progressive quantization scheme which gradually decreases the bit-width from high-precision to low-precision during training.
Scalable Place Recognition Under Appearance Change for Autonomous Driving
Our experiments show that, compared to state-of-the-art techniques, our method has much greater potential for large-scale place recognition for autonomous driving.
A Generalized Framework for Edge-preserving and Structure-preserving Image Smoothing
In this paper, a non-convex non-smooth optimization framework is proposed to achieve diverse smoothing natures where even contradictive smoothing behaviors can be achieved.
Social-BiGAT: Multimodal Trajectory Forecasting using Bicycle-GAN and Graph Attention Networks
This problem is compounded by the presence of social interactions between humans and their physical interactions with the scene.
Ranked #17 on
Trajectory Prediction
on ETH/UCY
CVPR19 Tracking and Detection Challenge: How crowded can it get?
Standardized benchmarks are crucial for the majority of computer vision applications.
Seeing Behind Things: Extending Semantic Segmentation to Occluded Regions
In our experiments we demonstrate that a CNN trained by minimizing the proposed loss is able to predict semantic categories for visible and occluded object parts without requiring to increase the network size (compared to a standard segmentation task).
Bayesian Generative Active Deep Learning
Deep learning models have demonstrated outstanding performance in several problems, but their training process tends to require immense amounts of computational and human resources for training and labeling, constraining the types of problems that can be tackled.
Attention-guided Network for Ghost-free High Dynamic Range Imaging
Ghosting artifacts caused by moving objects or misalignments is a key challenge in high dynamic range (HDR) imaging for dynamic scenes.
A Theoretically Sound Upper Bound on the Triplet Loss for Improving the Efficiency of Deep Distance Metric Learning
Another approach explored in the field relies on an ad-hoc linearization (in terms of N) of the triplet loss that introduces class centroids, which must be optimized using the whole training set for each mini-batch - this means that a naive implementation of this approach has run-time complexity O(N^2).
Architecture Search of Dynamic Cells for Semantic Video Segmentation
In semantic video segmentation the goal is to acquire consistent dense semantic labelling across image frames.
Template-Based Automatic Search of Compact Semantic Segmentation Architectures
Automatic search of neural architectures for various vision and natural language tasks is becoming a prominent tool as it allows to discover high-performing structures on any dataset of interest.
Ranked #13 on
Semantic Segmentation
on CamVid
Training Quantized Neural Networks with a Full-precision Auxiliary Module
In this paper, we seek to tackle a challenge in training low-precision networks: the notorious difficulty in propagating gradient through a low-precision network due to the non-differentiable quantization function.
V2CNet: A Deep Learning Framework to Translate Videos to Commands for Robotic Manipulation
We propose V2CNet, a new deep learning framework to automatically translate the demonstration videos to commands that can be directly used in robotic applications.
RGBD Based Dimensional Decomposition Residual Network for 3D Semantic Scene Completion
RGB images differentiate from depth images as they carry more details about the color and texture information, which can be utilized as a vital complementary to depth for boosting the performance of 3D semantic scene completion (SSC).
Ranked #19 on
3D Semantic Scene Completion
on NYUv2
Self-supervised Learning for Single View Depth and Surface Normal Estimation
In this work we present a self-supervised learning framework to simultaneously train two Convolutional Neural Networks (CNNs) to predict depth and surface normals from a single image.
Ranked #62 on
Monocular Depth Estimation
on KITTI Eigen split
Generalized Intersection over Union: A Metric and A Loss for Bounding Box Regression
By incorporating this generalized $IoU$ ($GIoU$) as a loss into the state-of-the art object detection frameworks, we show a consistent improvement on their performance using both the standard, $IoU$ based, and new, $GIoU$ based, performance measures on popular object detection benchmarks such as PASCAL VOC and MS COCO.
Visual SLAM: Why Bundle Adjust?
Bundle adjustment plays a vital role in feature-based monocular SLAM.
Multi-modal Ensemble Classification for Generalized Zero Shot Learning
In this paper, we mitigate these issues by proposing a new GZSL method based on multi-modal training and testing processes, where the optimization explicitly promotes a balanced classification accuracy between seen and unseen classes.
Learning Pairwise Relationship for Multi-object Detection in Crowded Scenes
As the post-processing step for object detection, non-maximum suppression (GreedyNMS) is widely used in most of the detectors for many years.
Single-view Object Shape Reconstruction Using Deep Shape Prior and Silhouette
3D shape reconstruction from a single image is a highly ill-posed problem.
Structured Binary Neural Networks for Accurate Image Classification and Semantic Segmentation
In this paper, we propose to train convolutional neural networks (CNNs) with both binarized weights and activations, leading to quantized models specifically} for mobile devices with limited power capacity and computation resources.
Visual Localization Under Appearance Change: Filtering Approaches
Our approaches rely on local features with an encoding technique to represent an image as a single vector.
Scalable Deep $k$-Subspace Clustering
In this paper, we introduce a method that simultaneously learns an embedding space along subspaces within it to minimize a notion of reconstruction error, thus addressing the problem of subspace clustering in an end-to-end learning paradigm.
Fast Neural Architecture Search of Compact Semantic Segmentation Models via Auxiliary Cells
While most results in this domain have been achieved on image classification and language modelling problems, here we concentrate on dense per-pixel tasks, in particular, semantic image segmentation using fully convolutional networks.
Ranked #13 on
Semantic Segmentation
on PASCAL VOC 2012 val
Approximate Fisher Information Matrix to Characterise the Training of Deep Neural Networks
Furthermore, the proposed measurements also allow us to show that it is possible to optimise the training process with a new dynamic sampling training approach that continuously and automatically change the mini-batch size and learning rate during the training process.
Light-Weight RefineNet for Real-Time Semantic Segmentation
We consider an important task of effective and efficient semantic image segmentation.
Ranked #2 on
Real-Time Semantic Segmentation
on NYU Depth v2
Diagnostics in Semantic Segmentation
Over the past years, computer vision community has contributed to enormous progress in semantic image segmentation, a per-pixel classification task, crucial for dense scene understanding and rapidly becoming vital in lots of real-world applications, including driverless cars and medical imaging.
Pre and Post-hoc Diagnosis and Interpretation of Malignancy from Breast DCE-MRI
Conversely, traditional approaches follow a pre-hoc approach that initially localises suspicious areas that are subsequently classified to establish the breast malignancy -- this approach is trained using strongly annotated data (i. e., it needs a delineation and classification of all lesions in an image).
Real-Time Monocular Object-Model Aware Sparse SLAM
While sparse point-based SLAM methods provide accurate camera localization, the generated maps lack semantic information.
Real-Time Joint Semantic Segmentation and Depth Estimation Using Asymmetric Annotations
Deployment of deep learning models in robotics as sensory information extractors can be a daunting task to handle, even using generic GPU cards.
Ranked #6 on
Real-Time Semantic Segmentation
on NYU Depth v2
Efficient Dense Point Cloud Object Reconstruction using Deformation Vector Fields
Given a single image at an arbitrary viewpoint, a CNN predicts multiple surfaces, each in a canonical location relative to the object.
Deep Regression Tracking with Shrinkage Loss
Regression trackers directly learn a mapping from regularly dense samples of target objects to soft labels, which are usually generated by a Gaussian function, to estimate target positions.
Training Compact Neural Networks with Binary Weights and Low Precision Activations
In this paper, we propose to train a network with binary weights and low-bitwidth activations, designed especially for mobile devices with limited power consumption.
MatchBench: An Evaluation of Feature Matchers
This leads to a critical absence in this field that there is no standard datasets and evaluation metrics to evaluate different feature matchers fairly.
Multi-modal Cycle-consistent Generalized Zero-Shot Learning
In generalized zero shot learning (GZSL), the set of classes are split into seen and unseen classes, where training relies on the semantic features of the seen and unseen classes and the visual representations of only the seen classes, while testing uses the visual representations of the seen and unseen classes.
Ranked #5 on
Generalized Zero-Shot Learning
on SUN Attribute
Model Agnostic Saliency for Weakly Supervised Lesion Detection from Breast DCE-MRI
There is a heated debate on how to interpret the decisions provided by deep learning models (DLM), where the main approaches rely on the visualization of salient regions to interpret the DLM classification process.
Bayesian Semantic Instance Segmentation in Open Set World
In this paper, we present a novel open-set semantic instance segmentation approach capable of segmenting all known and unknown object classes in images, based on the output of an object detector trained on known object classes.
Bootstrapping the Performance of Webly Supervised Semantic Segmentation
In this work, we focus on weak supervision, developing a method for training a high-quality pixel-level classifier for semantic segmentation, using only image-level class labels as the provided ground-truth.
Training Medical Image Analysis Systems like Radiologists
This process bears no direct resemblance with radiologist training, which is based on solving a series of tasks of increasing difficulty, where each task involves the use of significantly smaller datasets than those used in machine learning.
Just-in-Time Reconstruction: Inpainting Sparse Maps using Single View Depth Predictors as Priors
Crucially, we obtain the confidence weights that parameterize the CRF model in a data-dependent manner via Convolutional Neural Networks (CNNs) which are trained to model the conditional depth error distributions given each source of input depth map and the associated RGB image.
Deep Perm-Set Net: Learn to predict sets with unknown permutation and cardinality using deep neural networks
We demonstrate the validity of this new formulation on two relevant vision problems: object detection, for which our formulation outperforms state-of-the-art detectors such as Faster R-CNN and YOLO, and a complex CAPTCHA test, where we observe that, surprisingly, our set based network acquired the ability of mimicking arithmetics without any rules being coded.
Structure Aware SLAM using Quadrics and Planes
Simultaneous Localization And Mapping (SLAM) is a fundamental problem in mobile robotics.
Object Captioning and Retrieval with Natural Language
The key idea of our approach is the use of object descriptions to provide the detailed understanding of an object.
Unsupervised Learning of Monocular Depth Estimation and Visual Odometry with Deep Feature Reconstruction
Despite learning based methods showing promising results in single view depth estimation and visual odometry, most existing approaches treat the tasks in a supervised manner.
Deep-6DPose: Recovering 6D Object Pose from a Single RGB Image
Detecting objects and their 6D poses from only RGB images is an important task for many robotic applications.
Binary Constrained Deep Hashing Network for Image Retrieval without Manual Annotation
However, training deep hashing networks for the task is challenging due to the binary constraints on the hash codes, the similarity preserving property, and the requirement for a vast amount of labelled images.
Are You Talking to Me? Reasoned Visual Dialog Generation through Adversarial Learning
The Visual Dialogue task requires an agent to engage in a conversation about an image with a human.
Ranked #4 on
Visual Dialog
on VisDial v0.9 val
Vision-and-Language Navigation: Interpreting visually-grounded navigation instructions in real environments
This is significant because a robot interpreting a natural-language navigation instruction on the basis of what it sees is carrying out a vision and language process that is similar to Visual Question Answering.
Ranked #10 on
Visual Navigation
on R2R
Parallel Attention: A Unified Framework for Visual Object Discovery through Dialogs and Queries
To this end we propose a unified framework, the ParalleL AttentioN (PLAN) network, to discover the object in an image that is being referred to in variable length natural expression descriptions, from short phrases query to long multi-round dialogs.
Learning Deeply Supervised Good Features to Match for Dense Monocular Reconstruction
Visual SLAM (Simultaneous Localization and Mapping) methods typically rely on handcrafted visual features or raw RGB values for establishing correspondences between images.
Towards Effective Low-bitwidth Convolutional Neural Networks
This paper tackles the problem of training a deep convolutional neural network with both low-precision weights and low-bitwidth activations.
A Bayesian Data Augmentation Approach for Learning Deep Models
Data augmentation is an essential part of the training process applied to deep learning models.
Towards Context-Aware Interaction Recognition for Visual Relationship Detection
The proposed method still builds one classifier for one interaction (as per type (ii) above), but the classifier built is adaptive to context via weights which are context dependent.
Addressing Challenging Place Recognition Tasks using Generative Adversarial Networks
In the process, meaningful feature spaces are learned for each domain, the distances in which can be used for the task of place recognition.
Robotics
SceneCut: Joint Geometric and Object Segmentation for Indoor Scenes
This paper presents SceneCut, a novel approach to jointly discover previously unseen objects and non-object surfaces using a single RGB-D image.
AffordanceNet: An End-to-End Deep Learning Approach for Object Affordance Detection
We propose AffordanceNet, a new deep learning approach to simultaneously detect multiple objects and their affordances from RGB images.
Joint Learning of Set Cardinality and State Distribution
We present a novel approach for learning to predict sets using deep learning.
Deep Subspace Clustering Networks
We present a novel deep neural network architecture for unsupervised subspace clustering.
Ranked #3 on
Image Clustering
on Extended Yale-B
Visual Question Answering with Memory-Augmented Networks
In this paper, we exploit a memory-augmented neural network to predict accurate answers to visual questions, even when those answers occur rarely in the training set.
"Maximizing rigidity" revisited: a convex programming approach for generic 3D shape reconstruction from multiple perspective views
Rigid structure-from-motion (RSfM) and non-rigid structure-from-motion (NRSfM) have long been treated in the literature as separate (different) problems.
Adaptive Low-Rank Kernel Subspace Clustering
In this paper, we present a kernel subspace clustering method that can handle non-linear models.
Care about you: towards large-scale human-centric visual relationship detection
In addressing this problem we first construct a large-scale human-centric visual relationship detection dataset (HCVRD), which provides many more types of relationship annotation (nearly 10K categories) than the previous released datasets.
Human-Object Interaction Detection
Relationship Detection
+1
Weakly Supervised Semantic Segmentation Based on Web Image Co-segmentation
Training a Fully Convolutional Network (FCN) for semantic segmentation requires a large number of masks with pixel level labelling, which involves a large amount of human labour and time for annotation.
Tracking the Trackers: An Analysis of the State of the Art in Multiple Object Tracking
Standardized benchmarks are crucial for the majority of computer vision applications.
Smart Mining for Deep Metric Learning
In this paper, we propose a novel deep metric learning method that combines the triplet model and the global structure of the embedding space.
A Branch-and-Bound Algorithm for Checkerboard Extraction in Camera-Laser Calibration
We formulate the checkerboard extraction as a combinatorial optimization problem with a clear cut objective function.
Towards Context-aware Interaction Recognition
Recognizing how objects interact with each other is a crucial task in visual recognition.
Learning Multi-level Region Consistency with Dense Multi-label Networks for Semantic Segmentation
Semantic image segmentation is a fundamental task in image understanding.
Deep Learning Features at Scale for Visual Place Recognition
The success of deep learning techniques in the computer vision domain has triggered a range of initial investigations into their utility for visual place recognition, all using generic features from networks that were trained for other types of recognition tasks.
From Motion Blur to Motion Flow: a Deep Learning Solution for Removing Heterogeneous Motion Blur
The critical observation underpinning our approach is thus that learning the motion flow instead allows the model to focus on the cause of the blur, irrespective of the image content.
Attend in groups: a weakly-supervised deep learning framework for learning from web data
Large-scale datasets have driven the rapid development of deep neural networks for visual recognition.
DeepSetNet: Predicting Sets with Deep Neural Networks
This paper addresses the task of set prediction using deep learning.
RefineNet: Multi-Path Refinement Networks for High-Resolution Semantic Segmentation
Recently, very deep convolutional neural networks (CNNs) have shown outstanding performance in object recognition and have also been the first choice for dense classification problems such as semantic segmentation.
Ranked #13 on
Semantic Segmentation
on Trans10K
Meaningful Maps With Object-Oriented Semantic Mapping
For intelligent robots to interact in meaningful ways with their environment, they must understand both the geometric and semantic properties of the scene surrounding them.
Robotics
Exploiting Temporal Information for DCNN-based Fine-Grained Object Classification
Fine-grained classification is a relatively new field that has concentrated on using information from a single image, while ignoring the enormous potential of using video data to improve classification.
Past, Present, and Future of Simultaneous Localization And Mapping: Towards the Robust-Perception Age
Simultaneous Localization and Mapping (SLAM)consists in the concurrent construction of a model of the environment (the map), and the estimation of the state of the robot moving within it.
Robotics
Joint Probabilistic Matching Using m-Best Solutions
Matching between two sets of objects is typically approached by finding the object pairs that collectively maximize the joint matching score.
Efficient Point Process Inference for Large-Scale Object Detection
We tackle the problem of large-scale object detection in images, where the number of objects can be arbitrarily large, and can exhibit significant overlap/occlusion.
Online Multi-Target Tracking Using Recurrent Neural Networks
Here, we propose for the first time, an end-to-end learning approach for online multi-target tracking.
Unsupervised CNN for Single View Depth Estimation: Geometry to the Rescue
In this work we propose a unsupervised framework to learn a deep convolutional neural network for single view depth predic- tion, without requiring a pre-training stage or annotated ground truth depths.
Non-linear Dimensionality Regularizer for Solving Inverse Problems
Additionally, we evaluate our method on the challenging problem of Non-Rigid Structure from Motion and our approach delivers promising results on CMU mocap dataset despite the presence of significant occlusions and noise.
Exploring Context with Deep Structured models for Semantic Segmentation
We formulate deep structured models by combining CNNs and Conditional Random Fields (CRFs) for learning the patch-patch context between image regions.
Fast Training of Triplet-based Deep Binary Embedding Networks
To solve the first stage, we design a large-scale high-order binary codes inference algorithm to reduce the high-order objective to a standard binary quadratic problem such that graph cuts can be used to efficiently infer the binary code which serve as the label of each training datum.
MOT16: A Benchmark for Multi-Object Tracking
Recently, a new benchmark for Multiple Object Tracking, MOTChallenge, was launched with the goal of collecting existing and new data and creating a framework for the standardized evaluation of multiple object tracking methods.
Learning Local Image Descriptors with Deep Siamese and Triplet Convolutional Networks by Minimising Global Loss Functions
Current results from machine learning show that replacing this siamese by a triplet network can improve the classification accuracy in several problems, but this has yet to be demonstrated for local image descriptor learning.
Hierarchical Higher-Order Regression Forest Fields: An Application to 3D Indoor Scene Labelling
Specifically, we relax the labelling problem to a regression, and generalize the higher-order associative P n Potts model to a new family of arbitrary higher-order models based on regression forests.
Joint Probabilistic Data Association Revisited
In this paper, we revisit the joint probabilistic data association (JPDA) technique and propose a novel solution based on recent developments in finding the m-best solutions to an integer linear program.
Deeply Learning the Messages in Message Passing Inference
The network output dimension for message estimation is the same as the number of classes, in contrast to the network output for general CNN potential functions in CRFs, which is exponential in the order of the potentials.
The k-Support Norm and Convex Envelopes of Cardinality and Rank
Sparsity, or cardinality, as a tool for feature selection is extremely common in a vast number of current computer vision applications.
Joint Tracking and Segmentation of Multiple Targets
Tracking-by-detection has proven to be the most successful strategy to address the task of tracking multiple targets in unconstrained scenarios.
MOTChallenge 2015: Towards a Benchmark for Multi-Target Tracking
We discuss the challenges of creating such a framework, collecting existing and new data, gathering state-of-the-art methods to be tested on the datasets, and finally creating a unified evaluation system.
Efficient piecewise training of deep structured models for semantic segmentation
Recent advances in semantic image segmentation have mostly been achieved by training deep convolutional neural networks (CNNs).
Ranked #54 on
Semantic Segmentation
on PASCAL Context
Learning Depth from Single Monocular Images Using Deep Convolutional Neural Fields
Therefore, here we present a deep convolutional neural field model for estimating depths from single monocular images, aiming to jointly explore the capacity of deep CNN and continuous CRF.
Dense 3D Face Correspondence
A deformable model (K3DM) is constructed from the dense corresponded faces and an algorithm is proposed for morphing the K3DM to fit unseen faces.
Online Unsupervised Feature Learning for Visual Tracking
Feature encoding with respect to an over-complete dictionary learned by unsupervised methods, followed by spatial pyramid pooling, and linear classification, has exhibited powerful strength in various vision applications.
Dense Reconstruction Using 3D Object Shape Priors
More specifically, we automatically augment our SLAM system with object specific identity, together with 6D pose and additional shape degrees of freedom for the object(s) of known class in the scene, combining image data and depth information for the pose and shape recovery.
