Uncovering Hidden Challenges in Query-Based Video Moment Retrieval (BMVC 2020)

Uncovering Hidden Challenges in Query-Based Video Moment Retrieval (BMVC 2020)

ECCV 2020 - TVR: A Large-Scale Dataset for Video-Subtitle Moment Retrieval (1min version)Подробнее

ECCV 2020 - TVR: A Large-Scale Dataset for Video-Subtitle Moment Retrieval (1min version)

Query-Dependent Video Representation for Moment Retrieval and Highlight Detection (CVPR 2023)Подробнее

Query-Dependent Video Representation for Moment Retrieval and Highlight Detection (CVPR 2023)

ECCV 2020 - TVR: A Large-Scale Dataset for Video-Subtitle Moment Retrieval (9mins version)Подробнее

ECCV 2020 - TVR: A Large-Scale Dataset for Video-Subtitle Moment Retrieval (9mins version)

RODEO: Replay for Online Object Detection ( BMVC 2020)Подробнее

RODEO: Replay for Online Object Detection ( BMVC 2020)

Mitigating Dataset Bias (BMVC 2020 Keynote)Подробнее

Mitigating Dataset Bias (BMVC 2020 Keynote)

Query-Dependent Video Representation for Moment Retrieval and Highlight DetectionПодробнее

Query-Dependent Video Representation for Moment Retrieval and Highlight Detection

Популярные ошибки фронтендеров новичков и как их избегатьПодробнее

Популярные ошибки фронтендеров новичков и как их избегать

789 - DORi: Discovering Object Relationships for Moment Localization of a NaturalLanguage Query inПодробнее

789 - DORi: Discovering Object Relationships for Moment Localization of a NaturalLanguage Query in

608 - Temporal Context Aggregation for Video Retrieval with Contrastive LearningПодробнее

608 - Temporal Context Aggregation for Video Retrieval with Contrastive Learning

Neighbourhood-Insensitive Point Cloud Normal Estimation Network (BMVC 2020 Oral)Подробнее

Neighbourhood-Insensitive Point Cloud Normal Estimation Network (BMVC 2020 Oral)

Zero-Shot Video Moment Retrieval From Frozen Vision-Language ModelsПодробнее

Zero-Shot Video Moment Retrieval From Frozen Vision-Language Models

Video Localization Made EasyПодробнее

Video Localization Made Easy

Teach Computers to Connect Videos and Text without Labeled Data - VideoClipПодробнее

Teach Computers to Connect Videos and Text without Labeled Data - VideoClip

2nd International Workshop on Video Retrieval Methods and Their LimitsПодробнее

2nd International Workshop on Video Retrieval Methods and Their Limits

1317 - LoGAN: Latent Graph Co-Attention Network for Weakly-Supervised Video Moment RetrievalПодробнее

1317 - LoGAN: Latent Graph Co-Attention Network for Weakly-Supervised Video Moment Retrieval