Linked e-resources
Details
Table of Contents
ByteTrack: Multi-Object Tracking by Associating Every Detection Box
Robust Multi-Object Tracking by Marginal Inference
PolarMOT: How Far Can Geometric Relations Take Us in 3D Multi-Object Tracking?
Particle Video Revisited: Tracking through Occlusions Using Point Trajectories
Tracking Objects As Pixel-Wise Distributions
CMT: Context-Matching-Guided Transformer for 3D Tracking in Point Clouds
Towards Generic 3D Tracking in RGBD Videos: Benchmark and Baseline
Hierarchical Latent Structure for Multi-modal Vehicle Trajectory Forecasting
AiATrack: Attention in Attention for Transformer Visual Tracking
Disentangling Architecture and Training for Optical Flow
A Perturbation-Constrained Adversarial Attack for Evaluating the Robustness of Optical Flow
Robust Landmark-Based Stent Tracking in X-Ray Fluoroscopy
Social ODE: Multi-agent Trajectory Forecasting with Neural Ordinary Differential Equations
Social-SSL: Self-Supervised Cross-Sequence Representation Learning Based on Transformers for Multi-agent Trajectory Prediction
Diverse Human Motion Prediction Guided by Multi-level Spatial- Temporal Anchors
Learning Pedestrian Group Representations for Multi-modal Trajectory Prediction
Sequential Multi-View Fusion Network for Fast LiDAR Point Motion Estimation
E-Graph: Minimal Solution for Rigid Rotation with Extensibility Graphs
Point Cloud Compression with Range Image-Based Entropy Model for Autonomous Driving
Joint Feature Learning and Relation Modeling for Tracking: A One-Stream Framework
MotionCLIP: Exposing Human Motion Generation to CLIP Space
Backbone Is All Your Need: A Simplified Architecture for Visual Object Tracking
Aware of the History: Trajectory Forecasting with the Local Behavior Data
Optical Flow Training under Limited Label Budget via Active Learning
Hierarchical Feature Embedding for Visual Tracking
Tackling Background Distraction in Video Object Segmentation
Social-Implicit: Rethinking Trajectory Prediction Evaluation and the Effectiveness of Implicit Maximum Likelihood Estimation
TEMOS: Generating Diverse Human Motions from Textual Descriptions
Tracking Every Thing in the Wild
HULC: 3D HUman Motion Capture with Pose Manifold SampLing and Dense Contact Guidance
Towards Sequence-Level Training for Visual Tracking
Learned Monocular Depth Priors in Visual-Inertial Initialization
Robust Visual Tracking by Segmentation
MeshLoc: Mesh-Based Visual Localization
S2F2: Single-Stage Flow Forecasting for Future Multiple Trajectories Prediction
Large-Displacement 3D Object Tracking with Hybrid Non-local Optimization
FEAR: Fast, Efficient, Accurate and Robust Visual Tracker
PREF: Predictability Regularized Neural Motion Fields
View Vertically: A Hierarchical Network for Trajectory Prediction via Fourier Spectrums
HVC-Net: Unifying Homography, Visibility, and Confidence Learning for Planar Object Tracking
RamGAN: Region Attentive Morphing GAN for Region-Level Makeup Transfer
SinNeRF: Training Neural Radiance Fields on Complex Scenes from a Single Image
Entropy-Driven Sampling and Training Scheme for Conditional Diffusion Generation.
Robust Multi-Object Tracking by Marginal Inference
PolarMOT: How Far Can Geometric Relations Take Us in 3D Multi-Object Tracking?
Particle Video Revisited: Tracking through Occlusions Using Point Trajectories
Tracking Objects As Pixel-Wise Distributions
CMT: Context-Matching-Guided Transformer for 3D Tracking in Point Clouds
Towards Generic 3D Tracking in RGBD Videos: Benchmark and Baseline
Hierarchical Latent Structure for Multi-modal Vehicle Trajectory Forecasting
AiATrack: Attention in Attention for Transformer Visual Tracking
Disentangling Architecture and Training for Optical Flow
A Perturbation-Constrained Adversarial Attack for Evaluating the Robustness of Optical Flow
Robust Landmark-Based Stent Tracking in X-Ray Fluoroscopy
Social ODE: Multi-agent Trajectory Forecasting with Neural Ordinary Differential Equations
Social-SSL: Self-Supervised Cross-Sequence Representation Learning Based on Transformers for Multi-agent Trajectory Prediction
Diverse Human Motion Prediction Guided by Multi-level Spatial- Temporal Anchors
Learning Pedestrian Group Representations for Multi-modal Trajectory Prediction
Sequential Multi-View Fusion Network for Fast LiDAR Point Motion Estimation
E-Graph: Minimal Solution for Rigid Rotation with Extensibility Graphs
Point Cloud Compression with Range Image-Based Entropy Model for Autonomous Driving
Joint Feature Learning and Relation Modeling for Tracking: A One-Stream Framework
MotionCLIP: Exposing Human Motion Generation to CLIP Space
Backbone Is All Your Need: A Simplified Architecture for Visual Object Tracking
Aware of the History: Trajectory Forecasting with the Local Behavior Data
Optical Flow Training under Limited Label Budget via Active Learning
Hierarchical Feature Embedding for Visual Tracking
Tackling Background Distraction in Video Object Segmentation
Social-Implicit: Rethinking Trajectory Prediction Evaluation and the Effectiveness of Implicit Maximum Likelihood Estimation
TEMOS: Generating Diverse Human Motions from Textual Descriptions
Tracking Every Thing in the Wild
HULC: 3D HUman Motion Capture with Pose Manifold SampLing and Dense Contact Guidance
Towards Sequence-Level Training for Visual Tracking
Learned Monocular Depth Priors in Visual-Inertial Initialization
Robust Visual Tracking by Segmentation
MeshLoc: Mesh-Based Visual Localization
S2F2: Single-Stage Flow Forecasting for Future Multiple Trajectories Prediction
Large-Displacement 3D Object Tracking with Hybrid Non-local Optimization
FEAR: Fast, Efficient, Accurate and Robust Visual Tracker
PREF: Predictability Regularized Neural Motion Fields
View Vertically: A Hierarchical Network for Trajectory Prediction via Fourier Spectrums
HVC-Net: Unifying Homography, Visibility, and Confidence Learning for Planar Object Tracking
RamGAN: Region Attentive Morphing GAN for Region-Level Makeup Transfer
SinNeRF: Training Neural Radiance Fields on Complex Scenes from a Single Image
Entropy-Driven Sampling and Training Scheme for Conditional Diffusion Generation.