TPAMI 2022 papers on Video
37 of the 583 papers published in TPAMI 2022 (6.3%) are on Video, compared with 8.5% at TPAMI 2021. They fall into 4 topics.
See TPAMI 2022 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 · 17 papers
- A Survey on Deep Learning Technique for Video Segmentation (297 citations)
- Low Cost and Latency Event Camera Background Activity Denoising (149 citations)
- DoTA: Unsupervised Detection of Traffic Anomaly in Driving Videos (142 citations)
- CAS(ME)3: A Third Generation Facial Spontaneous Micro-Expression Database with Depth Information and High Ecological Validity (134 citations)
- Recurrent Neural Networks for Snapshot Compressive Imaging (125 citations)
- Deep Video Prior for Video Consistency and Propagation (104 citations)
- Spatial-Temporal Transformer for Video Snapshot Compressive Imaging (85 citations)
- LSV-LP: Large-Scale Video-Based License Plate Detection and Recognition (51 citations)
- Formulating Event-based Image Reconstruction as a Linear Inverse Problem with Deep Regularization using Optical Flow (45 citations)
- SuperFast: 200× Video Frame Interpolation via Event Camera (40 citations)
- FVC: An End-to-End Framework towards Deep Video Compression in Feature Space (26 citations)
- Rolling Shutter Inversion: Bring Rolling Shutter Images to High Framerate Global Shutter Video (22 citations)
and 5 more in the interactive map.
Action recognition · 13 papers
- Human Action Recognition From Various Data Modalities: A Review (733 citations)
- Enhanced Spatio-Temporal Interaction Learning for Video Deraining: Faster and Better (273 citations)
- MMNet: A Model-Based Multimodal Network for Human Action Recognition in RGB-D Videos (157 citations)
- TN-ZSTAD: Transferable Network for Zero-Shot Temporal Activity Detection (107 citations)
- Deep Learning-Based Action Detection in Untrimmed Videos: A Survey (101 citations)
- Equivalent Classification Mapping for Weakly Supervised Temporal Action Localization (35 citations)
- Learning SpatioTemporal and Motion Features in a Unified 2D Network for Action Recognition (34 citations)
- Transferring Knowledge From Text to Video: Zero-Shot Anticipation for Procedural Actions (24 citations)
- Adaptive Two-Stream Consensus Network for Weakly-Supervised Temporal Action Localization (23 citations)
- Egocentric Action Recognition by Automatic Relation Modeling (19 citations)
- Uncertainty Guided Collaborative Training for Weakly Supervised and Unsupervised Temporal Action Localization (18 citations)
- Action Recognition From a Single Coded Image (16 citations)
and 1 more in the interactive map.
Video-language understanding · 5 papers
- Video Pivoting Unsupervised Multi-Modal Machine Translation (150 citations)
- WebUAV-3M: A Benchmark for Unveiling the Power of Million-Scale Deep UAV Tracking (61 citations)
- Video Joint Modelling Based on Hierarchical Transformer for Co-summarization (47 citations)
- Weakly-Supervised Video Object Grounding via Causal Intervention (21 citations)
- Text-Driven Video Acceleration: A Weakly-Supervised Reinforcement Learning Method (10 citations)
