Papers with Code 아카이브
Video Recognition
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 0
- 평가표
- 0
- 보존된 평가 기록
- 0
Video Recognition is a process of obtaining, processing, and analysing data that it receives from a visual source, specifically video.
논문
이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.
V4D:4D Convolutional Neural Networks for Video-level Representation Learning
Over-the-Air Adversarial Flickering Attacks against Video Recognition Networks
Symbiotic Attention with Privileged Information for Egocentric Action Recognition
Audiovisual SlowFast Networks for Video Recognition
Sparse Black-box Video Attack with Reinforcement Learning
Flow-Distilled IP Two-Stream Networks for Compressed Video Action Recognition
LiteEval: A Coarse-to-Fine Framework for Resource Efficient Video Recognition
Learning Efficient Video Representation with Video Shuffle Networks
TEINet: Towards an Efficient Architecture for Video Recognition
Heuristic Black-box Adversarial Attacks on Video Recognition Models
Mimic The Raw Domain: Accelerating Action Recognition in the Compressed Domain
Coverage Guided Testing for Recurrent Neural Networks
Learning to Localize Temporal Events in Large-scale Video Data
Training Kinetics in 15 Minutes: Large-scale Distributed Training on Videos
A Video Recognition Method by using Adaptive Structural Learning of Long Short Term Memory based Deep Belief Network
Scheduled Differentiable Architecture Search for Visual Recognition
Retro-Actions: Learning 'Close' by Time-Reversing 'Open' Videos
Explainable Deep Learning for Video Recognition Tasks: A Framework & Recommendations
Multi-Agent Reinforcement Learning Based Frame Sampling for Effective Untrimmed Video Recognition
Sequence Level Semantics Aggregation for Video Object Detection
testRNN: Coverage-guided Testing on Recurrent Neural Networks
Learning Spatio-Temporal Representation with Local and Global Diffusion
Design Light-weight 3D Convolutional Networks for Video Recognition Temporal Residual, Fully Separable Block, and Fast Algorithm
Large Scale Holistic Video Understanding
Early Detection of Injuries in MLB Pitchers from Video
Drop an Octave: Reducing Spatial Redundancy in Convolutional Neural Networks with Octave Convolution
Black-box Adversarial Attacks on Video Recognition Models
Attention Distillation for Learning Video Representations
Micro-Batch Training with Batch-Channel Normalization and Weight Standardization
Demonstration of Vector Flow Imaging using Convolutional Neural Networks
Collaborative Spatio-temporal Feature Learning for Video Action Recognition
DistInit: Learning Video Representations Without a Single Labeled Video
SlowFast Networks for Video Recognition
AdaFrame: Adaptive Frame Selection for Fast Video Recognition
Multi-Task Learning of Generalizable Representations for Video Action Recognition
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.