https://github.com/wangjk666/stts
공식 코드Efficient Video Transformers with Spatial-Temporal Token Selection
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
Efficient Video Transformers with Spatial-Temporal Token Selection
UntrimmedNets for Weakly Supervised Action Recognition and Detection
Deep Convolutional Pooling Transformer for Deepfake Detection
VideoUFO: A Million-Scale User-Focused Dataset for Text-to-Video Generation
VidProM: A Million-scale Real Prompt-Gallery Dataset for Text-to-Video Diffusion Models
Feature-compatible Progressive Learning for Video Copy Detection
Feature-compatible Progressive Learning for Video Copy Detection
Self-Supervised Learning for Semi-Supervised Temporal Action Proposal
PD-SORT: Occlusion-Robust Multi-Object Tracking Using Pseudo-Depth Cues
The Butterfly Effect of Model Editing: Few Edits Can Trigger Large Language Models Collapse
The Mirage of Model Editing: Revisiting Evaluation in the Wild
RALACs: Action Recognition in Autonomous Vehicles using Interaction Encoding and Optical Flow
History Repeats Itself: Human Motion Prediction via Motion Attention
Learning Trajectory Dependencies for Human Motion Prediction
Generating Smooth Pose Sequences for Diverse Human Motion Prediction
Weakly-supervised Action Transition Learning for Stochastic Human Motion Prediction
Trackastra: Transformer-based cell tracking for live-cell microscopy
Self-supervised Object Tracking with Cycle-consistent Siamese Networks
Learning Temporally Causal Latent Processes from General Temporal Data
TC-Bench: Benchmarking Temporal Compositionality in Text-to-Video and Image-to-Video Generation
Assessing Knowledge Editing in Language Models via Relation Perspective
Assessing Knowledge Editing in Language Models via Relation Perspective
BundleTrack: 6D Pose Tracking for Novel Objects without Instance or Category-Level 3D Models
Learning to Fuse Asymmetric Feature Maps in Siamese Trackers
Predictive Experience Replay for Continual Visual Control and Forecasting
Learning to Locate Visual Answer in Video Corpus Using Question
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.