TPAMI 2019 papers on Video
34 of the 304 papers published in TPAMI 2019 (11.2%) are on Video, compared with 7.3% at TPAMI 2018. They fall into 3 topics.
See TPAMI 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 · 16 papers
- High Speed and High Dynamic Range Video with an Event Camera (795 citations)
- MEMC-Net: Motion Estimation and Motion Compensation Driven Neural Network for Video Interpolation and Enhancement (375 citations)
- Weakly Supervised Learning with Multi-Stream CNN-LSTM-HMMs to Discover Sequential Parallelism in Sign Language Videos (363 citations)
- Revisiting Video Saliency Prediction in the Deep Learning Era (349 citations)
- MFQE 2.0: A New Approach for Multi-Frame Quality Enhancement on Compressed Video (265 citations)
- Video Anomaly Detection with Sparse Coding Inspired Deep Neural Networks (252 citations)
- Unsupervised Learning of a Hierarchical Spiking Neural Network for Optical Flow Estimation: From Events to Global Motion Perception (207 citations)
- Recurrent Temporal Aggregation Framework for Deep Video Inpainting (72 citations)
- A Temporally-Aware Interpolation Network for Video Frame Inpainting (58 citations)
- Gravitational Laws of Focus of Attention (50 citations)
- 3D Rigid Motion Segmentation with Mixed and Unknown Number of Models (46 citations)
- Learning Energy-Based Spatial-Temporal Generative ConvNets for Dynamic Patterns (45 citations)
and 4 more in the interactive map.
Action recognition · 12 papers
- NTU RGB+D 120: A Large-Scale Benchmark for 3D Human Activity Understanding (1,934 citations)
- Moments in Time Dataset: One Million Videos for Event Understanding (572 citations)
- View Adaptive Neural Networks for High Performance Skeleton-Based Human Action Recognition (537 citations)
- Coherence Constrained Graph LSTM for Group Activity Recognition (247 citations)
- Hierarchical Long Short-Term Concurrent Memory for Human Interaction Recognition (220 citations)
- Skeleton-Based Online Action Prediction Using Scale Selection Network (177 citations)
- Two-Stream Region Convolutional 3D Network for Temporal Activity Detection (51 citations)
- Sparse Coding of Shape Trajectories for Facial Expression and Action Recognition (46 citations)
- A Novel Dynamic Model Capturing Spatial and Temporal Patterns for Facial Expression Analysis (22 citations)
- Fine-Grained Video Captioning via Graph-based Multi-Granularity Interaction Learning (21 citations)
- Discriminative Video Representation Learning Using Support Vector Classifiers (12 citations)
- Structured Label Inference for Visual Understanding
Video-language understanding · 6 papers
- SEWA DB: A Rich Database for Audio-Visual Emotion and Sentiment Research in the Wild (272 citations)
- Hierarchical LSTMs with Adaptive Attention for Visual Captioning (256 citations)
- Saliency Prediction in the Deep Learning Era: Successes and Limitations (242 citations)
- Reconstruct and Represent Video Contents for Captioning via Reinforcement Learning (85 citations)
- Interpreting the Rhetoric of Visual Advertisements (40 citations)
- Sequence-to-Segments Networks for Detecting Segments in Videos (21 citations)
