Pioneers ViPro, the first attack to adversarially promote videos in text-to-video retrieval, using Modal Refinement to improve black-box transferability across multiple targets.
Use what you have: Video retrieval using representations from collaborative experts
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
representative citing papers
Proposes the first unified incomplete video-language model that processes missing modalities and serves as a plug-and-play module to boost existing VLMs on multi-modal tasks.
MetaCLIP curates balanced 400M-pair subsets from CommonCrawl that outperform CLIP data, reaching 70.8% zero-shot ImageNet accuracy on ViT-B versus CLIP's 68.3%.
GLCCL uses a Global-Local Interaction Module and Contrastive Score Consistency loss to align text and video semantics more efficiently than attention-based methods on MSR-VTT, DiDeMo, and VATEX.
VLM2Vec-V2 is a multimodal embedding model trained on an extended MMEB-V2 benchmark that adds video and visual document tasks and reports gains on both new and prior image benchmarks.
DREAM reports new state-of-the-art recall@1 scores of 49.4%, 49.7%, and 27.3% on MSRVTT, MSVD, and LSMDC by combining masked and permuted language modeling with cascaded group attention in vision.
citing papers explorer
-
Adversarial Video Promotion Against Text-to-Video Retrieval
Pioneers ViPro, the first attack to adversarially promote videos in text-to-video retrieval, using Modal Refinement to improve black-box transferability across multiple targets.
-
Towards Unified Vision-Language Models with Incomplete Multi-Modal Inputs
Proposes the first unified incomplete video-language model that processes missing modalities and serves as a plug-and-play module to boost existing VLMs on multi-modal tasks.
-
Demystifying CLIP Data
MetaCLIP curates balanced 400M-pair subsets from CommonCrawl that outperform CLIP data, reaching 70.8% zero-shot ImageNet accuracy on ViT-B versus CLIP's 68.3%.
-
Text-Video Retrieval With Global-Local Contrastive Consistency Learning
GLCCL uses a Global-Local Interaction Module and Contrastive Score Consistency loss to align text and video semantics more efficiently than attention-based methods on MSR-VTT, DiDeMo, and VATEX.
-
VLM2Vec-V2: Advancing Multimodal Embedding for Videos, Images, and Visual Documents
VLM2Vec-V2 is a multimodal embedding model trained on an extended MMEB-V2 benchmark that adds video and visual document tasks and reports gains on both new and prior image benchmarks.
-
DREAM: Extending Vision-Language Models with Dual-Objective Encoding for Cross-Modal Retrieval
DREAM reports new state-of-the-art recall@1 scores of 49.4%, 49.7%, and 27.3% on MSRVTT, MSVD, and LSMDC by combining masked and permuted language modeling with cascaded group attention in vision.