Stitch-a-Demo is a retrieval-based method that assembles visually coherent video demonstrations from multistep textual descriptions by training on weakly supervised procedural data with hard negatives.
Improving video-text retrieval by multi-stream corpus alignment and dual softmax loss
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
citation-role summary
background 1
method 1
citation-polarity summary
verdicts
UNVERDICTED 5polarities
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.
MoVA introduces modular asymmetric dual projections to handle temporal misalignment and semantic asymmetry in long video-text alignment.
InternVideo combines masked video modeling and video-language contrastive learning into a single foundation model that reaches state-of-the-art results on 39 video datasets including 91.1% top-1 on Kinetics-400.
citing papers explorer
-
Stitch-a-Demo: Video Demonstrations from Multistep Descriptions
Stitch-a-Demo is a retrieval-based method that assembles visually coherent video demonstrations from multistep textual descriptions by training on weakly supervised procedural data with hard negatives.
-
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.
-
MoVA: Learning Asymmetric Dual Projections for Modular Long Video-Text Alignment
MoVA introduces modular asymmetric dual projections to handle temporal misalignment and semantic asymmetry in long video-text alignment.
-
InternVideo: General Video Foundation Models via Generative and Discriminative Learning
InternVideo combines masked video modeling and video-language contrastive learning into a single foundation model that reaches state-of-the-art results on 39 video datasets including 91.1% top-1 on Kinetics-400.