AAAI 2020 accepted papers on Video
74 of the 1,610 papers accepted at AAAI 2020 (4.6%) are on Video, compared with 4.2% at AAAI 2019. They fall into 4 topics.
See AAAI 2020 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 · 31 papers
- Self-Attention ConvLSTM for Spatiotemporal Prediction (414 citations)
- Channel Attention Is All You Need for Video Frame Interpolation (353 citations)
- Spatial-Temporal Multi-Cue Network for Continuous Sign Language Recognition (247 citations)
- Motion-Attentive Transition for Zero-Shot Video Object Segmentation (188 citations)
- Pyramid Constrained Self-Attention Network for Fast Video Salient Object Detection (174 citations)
- Spatio-Temporal Deformable Convolution for Compressed Video Quality Enhancement (171 citations)
- Video Frame Interpolation via Deformable Separable Convolution (150 citations)
- Spatio-Temporal Attention-Based Neural Network for Credit Card Fraud Detection (140 citations)
- Every Frame Counts: Joint Learning of Video Segmentation and Optical Flow (81 citations)
- JSI-GAN: GAN-Based Joint Super-Resolution and Inverse Tone-Mapping with Pixel-Wise Task-Specific Filters for UHD HDR Video (81 citations)
- SalSAC: A Video Saliency Prediction Model with Shuffled Attentions and Correlation-Based ConvLSTM (71 citations)
- End-to-End Learning of Object Motion Estimation from Retinal Events for Event-Based Object Tracking (66 citations)
and 19 more in the interactive map.
Action recognition · 28 papers
- TEINet: Towards an Efficient Architecture for Video Recognition (272 citations)
- Background Suppression Network for Weakly-Supervised Temporal Action Localization (259 citations)
- Fast Learning of Temporal Action Proposal via Dense Boundary Generator (209 citations)
- Video Cloze Procedure for Self-Supervised Spatio-Temporal Learning (155 citations)
- Progressive Boundary Refinement Network for Temporal Action Detection (144 citations)
- STEP: Spatial Temporal Graph Convolutional Networks for Emotion Perception from Gaits (137 citations)
- An End-to-End Visual-Audio Attention Network for Emotion Recognition in User-Generated Videos (131 citations)
- Temporal Interlacing Network (107 citations)
- Adversarial Cross-Domain Action Recognition with Co-Attention (103 citations)
- Accurate Temporal Action Proposal Generation with Relation-Aware Pyramid Network (79 citations)
- Symbiotic Attention with Privileged Information for Egocentric Action Recognition (72 citations)
- Relational Prototypical Network for Weakly Supervised Temporal Action Localization (69 citations)
and 16 more in the interactive map.
Video-language understanding · 13 papers
- Learning 2D Temporal Adjacent Networks for Moment Localization with Natural Language (521 citations)
- Learning Relationships between Text, Audio, and Video via Deep Canonical Correlation for Multimodal Language Analysis (419 citations)
- Temporally Grounding Language Queries in Videos by Contextual Boundary-Aware Prediction (188 citations)
- Location-Aware Graph Convolutional Networks for Video Question Answering (178 citations)
- Weakly-Supervised Video Moment Retrieval via Semantic Completion Network (175 citations)
- Rethinking the Bottom-Up Framework for Query-Based Video Localization (170 citations)
- Divide and Conquer: Question-Guided Spatio-Temporal Contextual Attention for Video Question Answering (108 citations)
- KnowIT VQA: Answering Knowledge-Based Questions about Videos (78 citations)
- Convolutional Hierarchical Attention Network for Query-Focused Video Summarization (62 citations)
- An Efficient Framework for Dense Video Captioning (52 citations)
- Joint Commonsense and Relation Reasoning for Image and Video Captioning (51 citations)
- A Proposal-Based Approach for Activity Image-to-Video Retrieval (17 citations)
and 1 more in the interactive map.
