AAAI 2019 accepted papers on Video
48 of the 1,147 papers accepted at AAAI 2019 (4.2%) are on Video, compared with 4.5% at AAAI 2018. They fall into 4 topics.
See AAAI 2019 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 · 21 papers
- Where to Go Next: A Spatio-Temporal Gated Network for Next POI Recommendation (415 citations)
- STA: Spatial-Temporal Attention for Large-Scale Video-Based Person Re-Identification (231 citations)
- Spatial-Temporal Person Re-Identification (228 citations)
- Multi-Scale 3D Convolution Network for Video Based Person Re-Identification (186 citations)
- Video Inpainting by Jointly Learning Temporal Structure and Spatial Details (178 citations)
- Deep Video Frame Interpolation Using Cyclic Frame Generation (165 citations)
- Spatial and Temporal Mutual Promotion for Video-Based Person Re-Identification (151 citations)
- Discriminative Feature Learning for Unsupervised Video Summarization (142 citations)
- Motion Guided Spatial Attention for Video Captioning (134 citations)
- Cycle-SUM: Cycle-Consistent Adversarial LSTM Networks for Unsupervised Video Summarization (125 citations)
- Robust Anomaly Detection in Videos Using Multilevel Representations (109 citations)
- Popularity Prediction on Online Articles with Deep Fusion of Temporal Process and Content Features (100 citations)
and 9 more in the interactive map.
Action recognition · 14 papers
- Self-Supervised Video Representation Learning with Space-Time Cubic Puzzles (321 citations)
- I Know the Relationships: Zero-Shot Action Recognition via Two-Stream Graph Convolutional Networks and Knowledge Graphs (225 citations)
- Semantic Proposal for Activity Localization in Videos via Sentence Query (198 citations)
- StNet: Local and Global Spatial-Temporal Modeling for Action Recognition (155 citations)
- Segregated Temporal Assembly Recurrent Networks for Weakly Supervised Multiple Action Detection (89 citations)
- Learning Transferable Self-Attentive Representations for Action Recognition in Untrimmed Videos with Weak Supervision (69 citations)
- Attention-Aware Sampling via Deep Reinforcement Learning for Action Recognition (56 citations)
- Skeleton-Based Gesture Recognition Using Several Fully Connected Layers with Path Signature Features and Temporal Transformer Module (50 citations)
- Temporal Bilinear Networks for Video Action Recognition (40 citations)
- Action Knowledge Transfer for Action Prediction with Partial Videos (36 citations)
- Mode Variational LSTM Robust to Unseen Modes of Variation: Application to Facial Expression Recognition (36 citations)
- Video Imprint Segmentation for Temporal Action Detection in Untrimmed Videos (25 citations)
and 2 more in the interactive map.
Video-language understanding · 10 papers
- ActivityNet-QA: A Dataset for Understanding Complex Web Videos via Question Answering (359 citations)
- To Find Where You Talk: Temporal Sentence Localization in Video with Attention Based Location Regression (357 citations)
- Multilevel Language and Vision Integration for Text-to-Clip Retrieval (326 citations)
- Read, Watch, and Move: Reinforcement Learning for Temporally Grounding Natural Language Descriptions in Videos (165 citations)
- Temporal Deformable Convolutional Encoder-Decoder Networks for Video Captioning (112 citations)
- Localizing Natural Language in Videos (95 citations)
- HireNet: A Hierarchical Attention Model for the Automatic Analysis of Asynchronous Video Job Interviews (87 citations)
- Fully Convolutional Video Captioning with Coarse-to-Fine and Inherited Attention (17 citations)
- LiveBot: Generating Live Video Comments Based on Visual and Textual Contexts
- Structured Two-Stream Attention Network for Video Question Answering
