Search Results for author:
Found 40 papers, 18 papers with code
Robust Noisy Label Learning via Two-Stream Sample Distillation
Noisy label learning aims to learn robust networks under the supervision of noisy labels, which plays a critical role in deep learning.
Learning Instance-Aware Correspondences for Robust Multi-Instance Point Cloud Registration in Cluttered Scenes
The superpoint correspondences are then extended to instance candidates at the fine level according to the instance masks.
Prediction of Vessel Arrival Time to Pilotage Area Using Multi-Data Fusion and Deep Learning
This paper investigates the prediction of vessels' arrival time to the pilotage area using multi-data fusion and deep learning approaches.
Delocate: Detection and Localization for Deepfake Videos with Randomly-Located Tampered Traces
Deepfake videos are becoming increasingly realistic, showing subtle tampering traces on facial areasthat vary between frames.
Multi-Prompts Learning with Cross-Modal Alignment for Attribute-based Person Re-Identification
Thereby, this paper explores the potential of using the generated multiple person attributes as prompts in ReID tasks with off-the-shelf (large) models for more accurate retrieval results.
Single-Shot and Multi-Shot Feature Learning for Multi-Object Tracking
In this paper, we propose a simple yet effective two-stage feature learning paradigm to jointly learn single-shot and multi-shot features for different targets, so as to achieve robust data association in the tracking process.
Recap: Detecting Deepfake Video with Unpredictable Tampered Traces via Recovering Faces and Mapping Recovered Faces
In the recovering stage, the model focuses on randomly masking regions of interest (ROIs) and reconstructing real faces without unpredictable tampered traces, resulting in a relatively good recovery effect for real faces while a poor recovery effect for fake faces.
2D3D-MATR: 2D-3D Matching Transformer for Detection-free Registration between Images and Point Clouds
The commonly adopted detect-then-match approach to registration finds difficulties in the cross-modality cases due to the incompatible keypoint detection and inconsistent feature description.
GeoTransformer: Fast and Robust Point Cloud Registration with Geometric Transformer
They seek correspondences over downsampled superpoints, which are then propagated to dense points.
Ranked #5 on
Point Cloud Registration
on FP-O-H
Tensorformer: Normalized Matrix Attention Transformer for High-quality Point Cloud Reconstruction
Surface reconstruction from raw point clouds has been studied for decades in the computer graphics community, which is highly demanded by modeling and rendering applications nowadays.
Decoupled Diffusion Models: Simultaneous Image to Zero and Zero to Noise
We propose decoupled diffusion models (DDMs) for high-quality (un)conditioned image generation in less than 10 function evaluations.
MotionTrack: Learning Robust Short-term and Long-term Motions for Multi-Object Tracking
For dense crowds, we design a novel Interaction Module to learn interaction-aware motions from short-term trajectories, which can estimate the complex movement of each target.
Deep Graph-based Spatial Consistency for Robust Non-rigid Point Cloud Registration
We first design a local spatial consistency measure over the deformation graph of the point cloud, which evaluates the spatial compatibility only between the correspondences in the vicinity of a graph node.
Learning Accurate Template Matching with Differentiable Coarse-to-Fine Correspondence Refinement
To tackle the challenges, we propose an accurate template matching method based on differentiable coarse-to-fine correspondence refinement.
Rotation-Invariant Transformer for Point Cloud Matching
To this end, we introduce RoITr, a Rotation-Invariant Transformer to cope with the pose variations in the point cloud matching task.
Mover: Mask and Recovery based Facial Part Consistency Aware Method for Deepfake Video Detection
Specifically, given a real face image, we first pretrain a masked autoencoder to learn facial part consistency by dividing faces into three parts and randomly masking ROIs, which are then recovered based on the unmasked facial parts.
Task-Specific Context Decoupling for Object Detection
Classification and localization are two main sub-tasks in object detection.
RIGA: Rotation-Invariant and Globally-Aware Descriptors for Point Cloud Registration
More specifically, 3D structures of the whole frame are first represented by our global PPF signatures, from which structural descriptors are learned to help geometric descriptors sense the 3D world beyond local regions.
Unsupervised Voice-Face Representation Learning by Cross-Modal Prototype Contrast
We present an approach to learn voice-face representations from the talking face videos, without any identity labels.
Geometric Transformer for Fast and Robust Point Cloud Registration
Such sparse and loose matching requires contextual features capturing the geometric structure of the point clouds.
Multi-Modal Relational Graph for Cross-Modal Video Moment Retrieval
Toward this end, we contribute a multi-modal relational graph to capture the interactions among objects from the visual and textual content to identify the differences among similar video moment candidates.
A System for Efficiently Hunting for Cyber Threats in Computer Systems Using Threat Intelligence
Log-based cyber threat hunting has emerged as an important solution to counter sophisticated cyber attacks.
Enabling Efficient Cyber Threat Hunting With Cyber Threat Intelligence
Log-based cyber threat hunting has emerged as an important solution to counter sophisticated attacks.
Optimising Stochastic Routing for Taxi Fleets with Model Enhanced Reinforcement Learning
The future of mobility-as-a-Service (Maas)should embrace an integrated system of ride-hailing, street-hailing and ride-sharing with optimised intelligent vehicle routing in response to a real-time, stochastic demand pattern.
Semi-supervised Collaborative Filtering by Text-enhanced Domain Adaptation
This causes two difficulties in designing effective algorithms: first, the majority of users only have a few interactions with the system and there is no enough data for learning; second, there are no negative samples in the implicit feedbacks and it is a common practice to perform negative sampling to generate negative samples.
Sampler Design for Implicit Feedback Data by Noisy-label Robust Learning
We predict users' preferences with the model and learn it by maximizing likelihood of observed data labels, i. e., a user prefers her positive samples and has no interests in her unvoted samples.
Graph Convolutional Network for Recommendation with Low-pass Collaborative Filters
\textbf{G}raph \textbf{C}onvolutional \textbf{N}etwork (\textbf{GCN}) is widely used in graph data learning tasks such as recommendation.
ThunderNet: Towards Real-Time Generic Object Detection on Mobile Devices
In this paper, we investigate the effectiveness of two-stage detectors in real-time generic detection and propose a lightweight two-stage detector named ThunderNet.
Visually-aware Recommendation with Aesthetic Features
While recent developments on visually-aware recommender systems have taken the product image into account, none of them has considered the aesthetic aspect.
Spectrum-enhanced Pairwise Learning to Rank
However, there are some demerits of side information: (1) the extra data is not always available in all recommendation tasks; (2) it is only for items, there is seldom high-level feature describing users.
ThunderNet: Towards Real-time Generic Object Detection
In this paper, we investigate the effectiveness of two-stage detectors in real-time generic detection and propose a lightweight two-stage detector named ThunderNet.
Ranked #15 on
Object Detection
on PASCAL VOC 2007
Aesthetic-based Clothing Recommendation
Considering that the aesthetic preference varies significantly from user to user and by time, we then propose a new tensor factorization model to incorporate the aesthetic features in a personalized manner.
Loss Rank Mining: A General Hard Example Mining Method for Real-time Detectors
LRM is a general method for real-time detectors, as it utilizes the final feature map which exists in all real-time detectors to mine hard examples.
Diagonalwise Refactorization: An Efficient Training Method for Depthwise Convolutions
Depthwise convolutions provide significant performance benefits owing to the reduction in both parameters and mult-adds.
Merging and Evolution: Improving Convolutional Neural Networks for Mobile Applications
Compact neural networks are inclined to exploit "sparsely-connected" convolutions such as depthwise convolution and group convolution for employment in mobile applications.
FD-MobileNet: Improved MobileNet with a Fast Downsampling Strategy
Experiments on ILSVRC 2012 and PASCAL VOC 2007 datasets demonstrate that FD-MobileNet consistently outperforms MobileNet and achieves comparable results with ShuffleNet under different computational budgets, for instance, surpassing MobileNet by 5. 5% on the ILSVRC 2012 top-1 accuracy and 3. 6% on the VOC 2007 mAP under a complexity of 12 MFLOPs.
Visually Explainable Recommendation
By this, we can not only provide recommendation results to the users, but also tell the users why an item is recommended by providing intuitive visual highlights in a personalized manner.
Transfer Hashing with Privileged Information
Specifically, we extend the standard learning to hash method, Iterative Quantization (ITQ), in a transfer learning manner, namely ITQ+.
Simple and Efficient Learning using Privileged Information
The Support Vector Machine using Privileged Information (SVM+) has been proposed to train a classifier to utilize the additional privileged information that is only available in the training phase but not available in the test phase.
