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.
Disentangled representa- tion learning for text-video retrieval
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
verdicts
UNVERDICTED 5roles
background 2polarities
background 2representative citing papers
Socratic Models compose zero-shot multimodal reasoning by prompting pretrained language and vision models to exchange information and enable new capabilities without finetuning.
Short, simple captions describing single actions achieve higher retrieval recall than complex multi-step or fine-grained scene descriptions across all tested models.
PPLLaVA uses CLIP-based alignment and prompt-guided convolution-style pooling to reduce visual tokens 18x in Video LLMs, achieving SOTA results on captioning, QA, and long-form reasoning benchmarks with higher throughput.
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.
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.
-
Socratic Models: Composing Zero-Shot Multimodal Reasoning with Language
Socratic Models compose zero-shot multimodal reasoning by prompting pretrained language and vision models to exchange information and enable new capabilities without finetuning.
-
Understanding the Performance Plateau in Text-to-Video Retrieval: A Comprehensive Empirical and Linguistic Analysis
Short, simple captions describing single actions achieve higher retrieval recall than complex multi-step or fine-grained scene descriptions across all tested models.
-
PPLLaVA: Varied Video Sequence Understanding With Prompt Guidance
PPLLaVA uses CLIP-based alignment and prompt-guided convolution-style pooling to reduce visual tokens 18x in Video LLMs, achieving SOTA results on captioning, QA, and long-form reasoning benchmarks with higher throughput.
-
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.