Papers with Code 아카이브
Video Understanding
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 7
- 평가표
- 0
- 보존된 평가 기록
- 0
A crucial task of Video Understanding is to recognise and localise (in space and time) different actions or events appearing in the video.
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/sermanet/tcn
Time-Contrastive Networks: Self-Supervised Learning from Video
https://github.com/shallowlearn/sportsreid
https://github.com/sharegpt4omni/sharegpt4video
ShareGPT4Video: Improving Video Understanding and Generation with Better Captions
https://github.com/shashankskagnihotri/adv-corrected-ddcat-cospgd
Towards Deep Learning Models Resistant to Adversarial Attacks
https://github.com/shim0114/T2V-Diffusion-Search
Inference-Time Text-to-Video Alignment with Diffusion Latent Beam Search
https://github.com/shinkyo0513/VideoAttribution
Towards Visually Explaining Video Understanding Networks with Perturbation
https://github.com/shnhrtkyk/satellite-super-resolution
The 2018 PIRM Challenge on Perceptual Image Super-resolution
https://github.com/skyworkai/moe-plus-plus
https://github.com/skyworkai/moh
https://github.com/spicyww/vistr_mindspore
https://github.com/stefkim/stylegan-batik
The Unreasonable Effectiveness of Deep Features as a Perceptual Metric
https://github.com/stevedepp/yolo4asl
TSM: Temporal Shift Module for Efficient Video Understanding
https://github.com/subeeshvasu/2018_subeesh_epsr_eccvw
The 2018 PIRM Challenge on Perceptual Image Super-resolution
https://github.com/subpic/koniq
KonIQ-10k: An ecologically valid database for deep learning of blind image quality assessment
https://github.com/sunutf/TSM
TSM: Temporal Shift Module for Efficient Video Understanding
https://github.com/tanveer81/rgnet
https://github.com/taoyang1122/adapt-image-models
AIM: Adapting Image Models for Efficient Video Action Recognition
https://github.com/tejas-gokhale/AGAT
Test-Time Training with Self-Supervision for Generalization under Distribution Shifts
https://github.com/tencent-hunyuan/hunyuancustom
HunyuanCustom: A Multimodal-Driven Architecture for Customized Video Generation
https://github.com/tencent-hunyuan/hunyuanvideo
HunyuanVideo: A Systematic Framework For Large Video Generative Models
https://github.com/tengdahan/temporalalignnet
https://github.com/tensorflow/cleverhans
Towards Deep Learning Models Resistant to Adversarial Attacks
https://github.com/tensorflow/models/tree/archive/research/tcn
Time-Contrastive Networks: Self-Supervised Learning from Video
https://github.com/tensorflow/models/tree/master/research/object_detection
Context R-CNN: Long Term Temporal Context for Per-Camera Object Detection
https://github.com/tensorflow/models/tree/master/research/tcn
Time-Contrastive Networks: Self-Supervised Learning from Video
https://github.com/tetrachrome/subpixel
https://github.com/thomashopkins32/PGDAdversarialLearning
Towards Deep Learning Models Resistant to Adversarial Attacks
https://github.com/thswodnjs3/CSTA
Video Joint Modelling Based on Hierarchical Transformer for Co-summarization
https://github.com/tianhewu/assessor360
MANIQA: Multi-dimension Attention Network for No-Reference Image Quality Assessment
https://github.com/tianyu0207/CCD
Weakly-supervised Video Anomaly Detection with Robust Temporal Feature Magnitude Learning
https://github.com/tianyuan168326/EAN-Pytorch
PAN: Towards Fast Action Recognition via Learning Persistence of Appearance
https://github.com/tianzheng4/Distributionally-Adversarial-Attack
Towards Deep Learning Models Resistant to Adversarial Attacks
https://github.com/timothyhtimothy/fast-vqa-and-fastervqa
FAST-VQA: Efficient End-to-end Video Quality Assessment with Fragment Sampling
https://github.com/titu1994/neural-image-assessment
https://github.com/towhee-io/towhee
Actor-Context-Actor Relation Network for Spatio-Temporal Action Localization
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.