conftrace_
← Processing
Computer Vision › Processing ›

Video Understanding

2,296 papers

Papers per year

59
164
423
'15
'20
'25

Papers

Bridge To Answer: Structure-Aware Graph Interaction Network for Video Question Answering CVPR 2021
Structured Multi-Level Interaction Network for Video Moment Localization via Language Query CVPR 2021
Behavior-Driven Synthesis of Human Dynamics CVPR 2021
Weakly Supervised Video Salient Object Detection CVPR 2021
Learning To Associate Every Segment for Video Panoptic Segmentation CVPR 2021
Three Birds with One Stone: Multi-Task Temporal Action Detection via Recycling Temporal Annotations CVPR 2021
On Semantic Similarity in Video Retrieval CVPR 2021
Hierarchical Video Prediction Using Relational Layouts for Human-Object Interactions CVPR 2021
Multi-Modal Fusion Transformer for End-to-End Autonomous Driving CVPR 2021
Learning Position and Target Consistency for Memory-Based Video Object Segmentation CVPR 2021
Representation Learning via Global Temporal Alignment and Cycle-Consistency CVPR 2021
VDSM: Unsupervised Video Disentanglement With State-Space Modeling and Deep Mixtures of Experts CVPR 2021
Polygonal Point Set Tracking CVPR 2021
Tracking Pedestrian Heads in Dense Crowd CVPR 2021
Embracing Uncertainty: Decoupling and De-Bias for Robust Temporal Grounding CVPR 2021
Video Object Segmentation Using Global and Instance Embedding Learning CVPR 2021
Target-Aware Object Discovery and Association for Unsupervised Video Multi-Object Segmentation CVPR 2021
Towards Extremely Compact RNNs for Video Recognition With Fully Decomposed Hierarchical Tucker Structure CVPR 2021
Less Is More: ClipBERT for Video-and-Language Learning via Sparse Sampling CVPR 2021
Anchor-Constrained Viterbi for Set-Supervised Action Segmentation CVPR 2021
Learning Goals From Failure CVPR 2021
Deep Analysis of CNN-Based Spatio-Temporal Representations for Action Recognition CVPR 2021
SG-Net: Spatial Granularity Network for One-Stage Video Instance Segmentation CVPR 2021
No Frame Left Behind: Full Video Action Recognition CVPR 2021
WOAD: Weakly Supervised Online Action Detection in Untrimmed Videos CVPR 2021