Zero-Shot Video Retrieval
8개 벤치마크 · 논문 41편 · 이 태스크의 논문 보기 →
Benchmarks
MSR-VTT
DiDeMo
LSMDC
MSVD
ActivityNet
YouCook2
VATEX
MSR-VTT-full
Most implemented
LanguageBind: Extending Video-Language Pretraining to N-modality by Language-based Semantic Alignment
VATT: Transformers for Multimodal Self-Supervised Learning from Raw Video, Audio and Text
CLIP4Clip: An Empirical Study of CLIP for End to End Video Clip Retrieval
Frozen in Time: A Joint Video and Image Encoder for End-to-End Retrieval
Papers
VeRVE: Versatile Retrieval for Videos via Unified Embeddings
Modern video retrieval systems are expected to handle diverse tasks ranging from corpus-level retrieval, fine-grained moment localization to flexible multimodal querying. Specialized architectures achieve strong retrieva…
Zero-shot Moment RetrievalZero-Shot Video RetrievalMake Your Training Flexible: Towards Deployment-Efficient Video Models
Popular video training methods mainly operate on a fixed number of tokens sampled from a predetermined spatiotemporal grid, resulting in sub-optimal accuracy-computation trade-offs due to inherent video redundancy. They …
Action ClassificationZero-Shot Video RetrievalGramian Multimodal Representation Learning and Alignment
Human perception integrates multiple modalities, such as vision, hearing, and language, into a unified understanding of the surrounding reality. While recent multimodal models have achieved significant progress by aligni…
Contrastive LearningRepresentation LearningText RetrievalVideo Classification+3InternVideo2: Scaling Foundation Models for Multimodal Video Understanding
We introduce InternVideo2, a new family of video foundation models (ViFM) that achieve the state-of-the-art results in video recognition, video-text tasks, and video-centric dialogue. Our core design is a progressive tra…
Action ClassificationAction RecognitionAudio ClassificationContrastive Learning+13vid-TLDR: Training Free Token merging for Light-weight Video Transformer
Video Transformers have become the prevalent solution for various video downstream tasks with superior expressive power and flexibility. However, these video transformers suffer from heavy computational costs induced by …
Action RecognitionComputational EfficiencyText RetrievalVideo Question Answering+5OmniVec2 - A Novel Transformer based Network for Large Scale Multimodal and Multitask Learning
We present a novel multimodal multitask network and associated training algorithm. The method is capable of ingesting data from approximately 12 different modalities namely image video audio text depth point cloud ti…
3D Point Cloud ClassificationAction ClassificationAction RecognitionAudio Classification+6