TPAMI 2021 papers on Video
44 of the 516 papers published in TPAMI 2021 (8.5%) are on Video, compared with 9.0% at TPAMI 2020. They fall into 4 topics.
See TPAMI 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 · 22 papers
- Low-Light Image and Video Enhancement Using Deep Learning: A Survey (723 citations)
- Video-based Facial Micro-Expression Analysis: A Survey of Datasets, Features and Algorithms (341 citations)
- A Background-Agnostic Framework with Adversarial Training for Abnormal Event Detection in Video (206 citations)
- Multiple Video Frame Interpolation via Enhanced Deformable Separable Convolution (176 citations)
- Collaborative Video Object Segmentation by Multi-Scale Foreground-Background Integration (161 citations)
- Future Frame Prediction Network for Video Anomaly Detection (138 citations)
- Plug-and-Play Algorithms for Video Snapshot Compressive Imaging (128 citations)
- Referring Segmentation in Images and Videos with Cross-Modal Self-Attention Network (94 citations)
- Moving Vehicle Detection for Remote Sensing Video Surveillance with Nonstationary Satellite Platform (74 citations)
- Event-Stream Representation for Human Gaits Identification Using Deep Neural Networks (68 citations)
- TRACK: A New Method from a Re-examination of Deep Architectures for Head Motion Prediction in 360-degree Videos (62 citations)
- Globally-Optimal Contrast Maximisation for Event Cameras (49 citations)
and 10 more in the interactive map.
Action recognition · 13 papers
- In the Eye of the Beholder: Gaze and Actions in First Person Video (102 citations)
- Graph Convolutional Module for Temporal Action Localization in Videos (95 citations)
- Multi-Moments in Time: Learning and Interpreting Models for Multi-Action Video Understanding (85 citations)
- Tensor Representations for Action Recognition (83 citations)
- Background-Click Supervision for Temporal Action Localization (82 citations)
- Self-Regulated Learning for Egocentric Video Activity Anticipation (67 citations)
- Depthwise Spatio-Temporal STFT Convolutional Neural Networks for Human Action Recognition (59 citations)
- Forecasting Action Through Contact Representations From First Person Video (57 citations)
- Multi-Dataset, Multitask Learning of Egocentric Vision Tasks (38 citations)
- Learning to Recognize Actions on Objects in Egocentric Video With Attention Dictionaries (20 citations)
- Two-Branch Relational Prototypical Network for Weakly Supervised Temporal Action Localization (20 citations)
- Fast Weakly Supervised Action Segmentation Using Mutual Consistency
and 1 more in the interactive map.
Video-language understanding · 7 papers
- Dual Encoding for Video Retrieval by Text (220 citations)
- Reconstructive Sequence-Graph Network for Video Summarization (131 citations)
- Natural Language Video Localization: A Revisit in Span-based Question Answering Framework (93 citations)
- Multi-Scale 2D Temporal Adjacency Networks for Moment Localization With Natural Language (79 citations)
- Aligning Source Visual and Target Language Domains for Unpaired Video Captioning (24 citations)
- Saying the Unseen: Video Descriptions via Dialog Agents
- Syntax Customized Video Captioning by Imitating Exemplar Sentences
Video generation · 2 papers
- One-Shot Imitation Drone Filming of Human Motion Videos (19 citations)
- Generating Personalized Summaries of Day Long Egocentric Videos (18 citations)
