Search Results for author:
Found 57 papers, 18 papers with code
Learning Tracking Representations from Single Point Annotations
In this paper, we propose to learn tracking representations from single point annotations (i. e., 4. 5x faster to annotate than the traditional bounding box) in a weakly supervised manner.
A Fixed-Point Approach to Unified Prompt-Based Counting
Additionally, a contrastive training scheme is implemented to mitigate dataset bias inherent in current class-agnostic counting datasets, a strategy whose effectiveness is confirmed by our ablation study.
Robust Unsupervised Crowd Counting and Localization with Adaptive Resolution SAM
The existing crowd counting models require extensive training data, which is time-consuming to annotate.
Edit Temporal-Consistent Videos with Image Diffusion Model
In addition to the utilization of a pretrained T2I 2D Unet for spatial content manipulation, we establish a dedicated temporal Unet architecture to faithfully capture the temporal coherence of the input video sequences.
Human Attention-Guided Explainable Artificial Intelligence for Computer Vision Models
We examined whether embedding human attention knowledge into saliency-based explainable AI (XAI) methods for computer vision models could enhance their plausibility and faithfulness.
DropMAE: Masked Autoencoders with Spatial-Attention Dropout for Tracking Tasks
However, we find that this simple baseline heavily relies on spatial cues while ignoring temporal relations for frame reconstruction, thus leading to sub-optimal temporal matching representations for VOT and VOS.
Ranked #1 on
Visual Object Tracking
on TrackingNet
(AUC metric)
TWINS: A Fine-Tuning Framework for Improved Transferability of Adversarial Robustness and Generalization
To better exploit the potential of pre-trained models in adversarial robustness, this paper focuses on the fine-tuning of an adversarially pre-trained model in various classification tasks.
Optimal Transport Minimization: Crowd Localization on Density Maps for Semi-Supervised Counting
In this paper, we propose the optimal transport minimization (OT-M) algorithm for crowd localization with density maps.
Scale-Prior Deformable Convolution for Exemplar-Guided Class-Agnostic Counting
Here we propose a scale-sensitive generalized loss to tackle this problem.
Ranked #5 on
Object Counting
on FSC147
Boosting Adversarial Robustness From The Perspective of Effective Margin Regularization
Our empirical study on feedforward DNNs demonstrates that the proposed effective margin regularization (EMR) learns large effective margins and boosts the adversarial robustness in both standard and adversarial training.
Pareto Optimization for Active Learning under Out-of-Distribution Data Scenarios
In this paper, we propose a sampling scheme, Monte-Carlo Pareto Optimization for Active Learning (POAL), which selects optimal subsets of unlabeled samples with fixed batch size from the unlabeled data pool.
An Empirical Study on Distribution Shift Robustness From the Perspective of Pre-Training and Data Augmentation
With our empirical result obtained from 1, 330 models, we provide the following main observations: 1) ERM combined with data augmentation can achieve state-of-the-art performance if we choose a proper pre-trained model respecting the data property; 2) specialized algorithms further improve the robustness on top of ERM when handling a specific type of distribution shift, e. g., GroupDRO for spurious correlation and CORAL for large-scale out-of-distribution data; 3) Comparing different pre-training modes, architectures and data sizes, we provide novel observations about pre-training on distribution shift, which sheds light on designing or selecting pre-training strategy for different kinds of distribution shifts.
Cross-View Cross-Scene Multi-View Crowd Counting
Multi-view crowd counting has been previously proposed to utilize multi-cameras to extend the field-of-view of a single camera, capturing more people in the scene, and improve counting performance for occluded people or those in low resolution.
On Distinctive Image Captioning via Comparing and Reweighting
First, we propose a distinctiveness metric -- between-set CIDEr (CIDErBtw) to evaluate the distinctiveness of a caption with respect to those of similar images.
A Comparative Survey of Deep Active Learning
In this work, We construct a DAL toolkit, DeepAL+, by re-implementing 19 highly-cited DAL methods.
A Lightweight and Detector-free 3D Single Object Tracker on Point Clouds
Recent works on 3D single object tracking treat the task as a target-specific 3D detection task, where an off-the-shelf 3D detector is commonly employed for the tracking.
Crowd Counting in the Frequency Domain
By transforming the density map into the frequency domain and using the nice properties of the characteristic function, we propose a novel method that is simple, effective, and efficient.
BEV-Net: Assessing Social Distancing Compliance by Joint People Localization and Geometric Reasoning
A dataset of crowd scenes with people annotations under a bird's eye view (BEV) and ground truth for metric distances is introduced, and several measures for the evaluation of social distance detection systems are proposed.
Group-based Distinctive Image Captioning with Memory Attention
In particular, we propose a group-based memory attention (GMA) module, which stores object features that are unique among the image group (i. e., with low similarity to objects in other images).
Multiple-criteria Based Active Learning with Fixed-size Determinantal Point Processes
In this paper, we introduce a multiple-criteria based active learning algorithm, which incorporates three complementary criteria, i. e., informativeness, representativeness and diversity, to make appropriate selections in the active learning rounds under different data types.
A Generalized Loss Function for Crowd Counting and Localization
In this paper, we investigate learning the density map representation through an unbalanced optimal transport problem, and propose a generalized loss function to learn density maps for crowd counting and localization.
Progressive Unsupervised Learning for Visual Object Tracking
In this paper, we propose a progressive unsupervised learning (PUL) framework, which entirely removes the need for annotated training videos in visual tracking.
Weight Rescaling: Effective and Robust Regularization for Deep Neural Networks with Batch Normalization
On the one hand, when the non-adaptive learning rate e. g. SGD with momentum is used, the effective learning rate continues to increase even after the initial training stage, which leads to an overfitting effect in many neural architectures.
Variational Nested Dropout
Nested dropout is a variant of dropout operation that is able to order network parameters or features based on the pre-defined importance during training.
Wide-Area Crowd Counting: Multi-View Fusion Networks for Counting in Large Scenes
We consider three versions of the fusion framework: the late fusion model fuses camera-view density map; the naive early fusion model fuses camera-view feature maps; and the multi-view multi-scale early fusion model ensures that features aligned to the same ground-plane point have consistent scales.
Improve Generalization and Robustness of Neural Networks via Weight Scale Shifting Invariant Regularizations
The derived regularizer is an upper bound for the input gradient of the network so minimizing the improved regularizer also benefits the adversarial robustness.
Tracking-by-Counting: Using Network Flows on Crowd Density Maps for Tracking Multiple Targets
State-of-the-art multi-object tracking~(MOT) methods follow the tracking-by-detection paradigm, where object trajectories are obtained by associating per-frame outputs of object detectors.
Compare and Reweight: Distinctive Image Captioning Using Similar Images Sets
A wide range of image captioning models has been developed, achieving significant improvement based on popular metrics, such as BLEU, CIDEr, and SPICE.
Fine-Grained Crowd Counting
Second, we propose a complementary attention model to share information between the two branches.
Single-Frame based Deep View Synchronization for Unsynchronized Multi-Camera Surveillance
To handle the issue of unsynchronized multi-cameras, in this paper, we propose a synchronization model that works in conjunction with existing DNN-based multi-view models, thus avoiding the redesign of the whole model.
Over-crowdedness Alert! Forecasting the Future Crowd Distribution
In this paper, we formulate a novel crowd analysis problem, in which we aim to predict the crowd distribution in the near future given sequential frames of a crowd video without any identity annotations.
3D Crowd Counting via Multi-View Fusion with 3D Gaussian Kernels
Unlike MVMS, we propose to solve the multi-view crowd counting task through 3D feature fusion with 3D scene-level density maps, instead of the 2D ground-plane ones.
Towards Diverse and Accurate Image Captions via Reinforcing Determinantal Point Process
Although significant progress has been made in the field of automatic image captioning, it is still a challenging task.
ROAM: Recurrently Optimizing Tracking Model
In this paper, we design a tracking model consisting of response generation and bounding box regression, where the first component produces a heat map to indicate the presence of the object at different positions and the second part regresses the relative bounding box shifts to anchors mounted on sliding-window locations.
Visual Tracking via Dynamic Memory Networks
The reading and writing process of the external memory is controlled by an LSTM network with the search feature map as input.
Accelerating Monte Carlo Bayesian Inference via Approximating Predictive Uncertainty over Simplex
In this work, assuming that the exact posterior or a decent approximation is obtained, we propose a generic framework to approximate the output probability distribution induced by model posterior with a parameterized model and in an amortized fashion.
Describing like humans: on diversity in image captioning
We find that there is still a large gap between the model and human performance in terms of both accuracy and diversity and the models that have optimized accuracy (CIDEr) have low diversity.
A Fully Bayesian Infinite Generative Model for Dynamic Texture Segmentation
A major limitation of these models concerns the automatic selection of a proper number of DTs.
Gated Hierarchical Attention for Image Captioning
Attention modules connecting encoder and decoders have been widely applied in the field of object recognition, image captioning, visual question answering and neural machine translation, and significantly improves the performance.
EMHMM Simulation Study
Eye Movement analysis with Hidden Markov Models (EMHMM) is a method for modeling eye fixation sequences using hidden Markov models (HMMs).
Fusing Crowd Density Maps and Visual Object Trackers for People Tracking in Crowd Scenes
While people tracking has been greatly improved over the recent years, crowd scenes remain particularly challenging for people tracking due to heavy occlusions, high crowd density, and significant appearance variation.
CNN+CNN: Convolutional Decoders for Image Captioning
We also test our model on the paragraph annotation dataset, and get higher CIDEr score compared with hierarchical LSTMs
Learning Dynamic Memory Networks for Object Tracking
In this paper, we propose a dynamic memory network to adapt the template to the target's appearance variations during tracking.
Recurrent Filter Learning for Visual Tracking
Recently using convolutional neural networks (CNNs) has gained popularity in visual tracking, due to its robust feature representation of images.
Beyond Counting: Comparisons of Density Maps for Crowd Analysis Tasks - Counting, Detection, and Tracking
The goal of this paper is to evaluate density maps generated by density estimation methods on a variety of crowd analysis tasks, including counting, detection, and tracking.
Color Orchestra: Ordering Color Palettes for Interpolation and Prediction
As artists often use their personal color themes in their paintings, making these palettes appear frequently in the dataset, we employed density estimation to capture the characteristics of palette data.
Crowd Counting by Adapting Convolutional Neural Networks with Side Information
In order to incorporate the available side information, we propose an adaptive convolutional neural network (ACNN), where the convolutional filter weights adapt to the current scene context via the side information.
Maximum-Margin Structured Learning with Deep Networks for 3D Human Pose Estimation
The score function is then the dot-product between the image and pose embeddings.
Ranked #312 on
3D Human Pose Estimation
on Human3.6M
Small Instance Detection by Integer Programming on Object Density Maps
For each region, a sliding window (ROI) is passed over the density map to calculate the instance count within each ROI.
Heterogeneous Multi-task Learning for Human Pose Estimation with Deep Convolutional Neural Network
We propose an heterogeneous multi-task learning framework for human pose estimation from monocular image with deep convolutional neural network.
Joint Motion Segmentation and Background Estimation in Dynamic Scenes
We derive an EM algorithm for estimating the parameters of the FBM.
Leveraging Long-Term Predictions and Online-Learning in Agent-based Multiple Person Tracking
We present a multiple-person tracking algorithm, based on combining particle filters and RVO, an agent-based crowd model that infers collision-free velocities so as to predict pedestrian's motion.
On Approximate Inference for Generalized Gaussian Process Models
In this paper, we consider efficient algorithms for approximate inference on GGPMs using the general form of the EFD.
Multivariate Generalized Gaussian Process Models
We propose a family of multivariate Gaussian process models for correlated outputs, based on assuming that the likelihood function takes the generic form of the multivariate exponential family distribution (EFD).
Crossing the Line: Crowd Counting by Integer Programming with Local Features
Next, the number of people is estimated in a set of overlapping sliding windows on the temporal slice image, using a regression function that maps from local features to a count.
The variational hierarchical EM algorithm for clustering hidden Markov models
In this paper, we derive a novel algorithm to cluster hidden Markov models (HMMs) according to their probability distributions.
