AAAI 2021 accepted papers on Video
55 of the 1,654 papers accepted at AAAI 2021 (3.3%) are on Video, compared with 4.6% at AAAI 2020. They fall into 4 topics.
See AAAI 2021 in the interactive map
Working on something in this area? Describe your idea in scime atlas to see the closest papers by meaning and how crowded the spot has become.
Topics and papers
Video segmentation and tracking · 26 papers
- Appearance-Motion Memory Consistency Network for Video Anomaly Detection (206 citations)
- Understanding Deformable Alignment in Video Super-Resolution (159 citations)
- Arbitrary Video Style Transfer via Multi-Channel Correlation (149 citations)
- Temporal ROI Align for Video Object Recognition (112 citations)
- GSNet: Learning Spatial-Temporal Correlations from Geographical and Semantic Aspects for Traffic Accident Risk Forecasting (103 citations)
- Hand-Model-Aware Sign Language Recognition (80 citations)
- Temporal Pyramid Network for Pedestrian Trajectory Prediction with Multi-Supervision (57 citations)
- CompFeat: Comprehensive Feature Aggregation for Video Instance Segmentation (49 citations)
- F2Net: Learning to Focus on the Foreground for Unsupervised Video Object Segmentation (33 citations)
- Quantum Cognitively Motivated Decision Fusion for Video Sentiment Analysis (32 citations)
- SSN3D: Self-Separated Network to Align Parts for 3D Convolution in Video Person Re-Identification (31 citations)
- Large Motion Video Super-Resolution with Dual Subnet and Multi-Stage Communicated Upsampling (29 citations)
and 14 more in the interactive map.
Action recognition · 16 papers
- SMART Frame Selection for Action Recognition (150 citations)
- A Hybrid Attention Mechanism for Weakly-Supervised Temporal Action Localization (131 citations)
- Weakly-supervised Temporal Action Localization by Uncertainty Modeling (125 citations)
- BSN++: Complementary Boundary Regressor with Scale-Balanced Relation Modeling for Temporal Action Proposal Generation (107 citations)
- SeCo: Exploring Sequence Supervision for Unsupervised Representation Learning (100 citations)
- RSPNet: Relative Speed Perception for Unsupervised Video Representation Learning (97 citations)
- ACSNet: Action-Context Separation Network for Weakly Supervised Temporal Action Localization (78 citations)
- MVFNet: Multi-View Fusion Network for Efficient Video Recognition (71 citations)
- Temporal Relational Modeling with Self-Supervision for Action Segmentation (48 citations)
- Enhancing Unsupervised Video Representation Learning by Decoupling the Scene and the Motion (47 citations)
- Weakly Supervised Temporal Action Localization Through Learning Explicit Subspaces for Action and Context (31 citations)
- Temporal Segmentation of Fine-gained Semantic Action: A Motion-Centered Figure Skating Dataset (24 citations)
and 4 more in the interactive map.
Video-language understanding · 10 papers
- Boundary Proposal Network for Two-stage Natural Language Video Localization (162 citations)
- Semantic Grouping Network for Video Captioning (150 citations)
- Proposal-Free Video Grounding with Contextual Pyramid Network (120 citations)
- Non-Autoregressive Coarse-to-Fine Video Captioning (76 citations)
- Dynamic Graph Representation Learning for Video Dialog via Multi-Modal Shuffled Transformers (37 citations)
- DramaQA: Character-Centered Video Story Understanding with Hierarchical QA (34 citations)
- Dense Events Grounding in Video (33 citations)
- Self-supervised Pre-training and Contrastive Representation Learning for Multiple-choice Video QA (33 citations)
- Structured Co-reference Graph Attention for Video-grounded Dialogue (26 citations)
- Augmented Partial Mutual Learning with Frame Masking for Video Captioning (24 citations)
