InstrAction pretrains video foundation models using action-centric data filtering, hard negatives, an Action Perceiver module, DTW-Align, and Masked Action Modeling to reduce static bias and outperform prior models on a new InstrAct Bench for semantic, procedural, and retrieval tasks.
Univilm: A unified video and language pre-training model for mul- timodal understanding and generation
8 Pith papers cite this work. Polarity classification is still indexing.
8
Pith papers citing it
citation-role summary
background 2
method 1
citation-polarity summary
representative citing papers
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.
Flamingo models reach new state-of-the-art few-shot results on image and video tasks by bridging frozen vision and language models with cross-attention layers trained on interleaved web-scale data.
LanguageBind aligns video, infrared, depth, and audio to a frozen language encoder via contrastive learning on the new VIDAL-10M dataset, extending video-language pretraining to N modalities.
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%.
The paper surveys hallucination in LLMs with an innovative taxonomy, factors, detection methods, benchmarks, mitigation strategies, and open research directions.
GIT achieves new state-of-the-art results on 12 vision-language benchmarks, including surpassing human performance on TextCaps, via a simplified single-encoder single-decoder transformer scaled on large pre-training data.
Survey organizing multimodal affective computing research around four NLP tasks, method paradigms, datasets, evaluation protocols, and future directions while releasing a resource repository.
citing papers explorer
-
Flamingo: a Visual Language Model for Few-Shot Learning
Flamingo models reach new state-of-the-art few-shot results on image and video tasks by bridging frozen vision and language models with cross-attention layers trained on interleaved web-scale data.