https://github.com/maryeon/whiten_mtd
공식 코드Let All be Whitened: Multi-teacher Distillation for Efficient Visual Retrieval
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
Let All be Whitened: Multi-teacher Distillation for Efficient Visual Retrieval
Exploring Iterative Refinement with Diffusion Models for Video Grounding
DARTH: Holistic Test-time Adaptation for Multiple Object Tracking
XMem++: Production-level Video Segmentation From Few Annotated Frames
VideoINSTA: Zero-shot Long Video Understanding via Informative Spatial-Temporal Reasoning with LLMs
Follow-Your-Click: Open-domain Regional Image Animation via Short Prompts
Follow Your Pose: Pose-Guided Text-to-Video Generation using Pose-Free Videos
MagicStick: Controllable Video Editing via Control Handle Transformations
MS-RNN: A Flexible Multi-Scale Framework for Spatiotemporal Predictive Learning
Accelerating Volumetric Medical Image Annotation via Short-Long Memory SAM 2
Accelerating Volumetric Medical Image Annotation via Short-Long Memory SAM 2
Video-ChatGPT: Towards Detailed Video Understanding via Large Vision and Language Models
VideoGPT+: Integrating Image and Video Encoders for Enhanced Video Understanding
Towards Real-time Video Compressive Sensing on Mobile Devices
BasicTAD: an Astounding RGB-Only Baseline for Temporal Action Detection
Progressive Attention on Multi-Level Dense Difference Maps for Generic Event Boundary Detection
Extracting Motion and Appearance via Inter-Frame Attention for Efficient Video Frame Interpolation
A Closer Look at Few-Shot Video Classification: A New Baseline and Benchmark
MeMOTR: Long-Term Memory-Augmented Transformer for Multi-Object Tracking
MGSampler: An Explainable Sampling Strategy for Video Action Recognition
Negative Sample Matters: A Renaissance of Metric Learning for Temporal Grounding
PointTAD: Multi-Label Temporal Action Detection with Learnable Query Points
SportsHHI: A Dataset for Human-Human Interaction Detection in Sports Videos
Adapting Short-Term Transformers for Action Detection in Untrimmed Videos
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.