Learning Video Representations from Large Language Models
Open accessThe DOI matches its Crossref record; 38 of the 38 references it cites were found in a registry or an index.
Abstract
We introduce LAVILA, a new approach to learning video-language representations by leveraging Large Language Models (LLMs). We repurpose pre-trained LLMs to be conditioned on visual input, and finetune them to create automatic video narrators. Our auto-generated narrations offer a number of advantages, including dense coverage of long videos, better temporal synchronization of the visual information and text, and much higher diversity of text. The video-language embedding learned contrastively with these narrations outperforms the previous state-of-the-art on multiple first-person and third-person video tasks, both in zero-shot and finetuned setups. Most notably, Lavilaobtains an absolute gain of 10.1% on EGTEA classification and 5.9% Epic-Kitchens-100 multi-instance retrieval benchmarks. Furthermore, LaVilatrained with only half the narrations from the Ego4D dataset outperforms models trained on the full set, and shows positive scaling behavior on increasing pre-training data and model size.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.90 · Cited by 235,474
Hochreiter, S., & Schmidhuber, J. (1997) · Neural Computation · doi:10.1162/neco.1997.9.8.1735 · Cited by 102,318
ImageNet: A large-scale hierarchical image database
Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K., & Fei-Fei, L. (2009) · 2009 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2009.5206848 · Cited by 65,333
An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., Gelly, S., et al. (2020) · arXiv · doi:10.48550/arxiv.2010.11929 · Cited by 47,472
Language Models are Few-Shot Learners
Brown, T. B., Mann, B., Ryder, N., Subbiah, M., Kaplan, J., Dhariwal, P., Neelakantan, A., Shyam, P., Sastry, G., Askell, A., et al. (2020) · arXiv · doi:10.48550/arxiv.2005.14165 · Cited by 23,372
Learning Transferable Visual Models From Natural Language Supervision
Radford, A., Kim, J. W., Hallacy, C., Ramesh, A., Goh, G., Agarwal, S., Sastry, G., Askell, A., Mishkin, P., Clark, J., et al. (2021) · arXiv · doi:10.48550/arxiv.2103.00020 · Cited by 15,293
Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer
Raffel, C., Shazeer, N., Roberts, A., Lee, K., Narang, S., Matena, M., Zhou, Y., Li, W., & Liu, P. J. (2019) · arXiv · doi:10.48550/arxiv.1910.10683 · Cited by 10,929
Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset
Carreira, J., & Zisserman, A. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.502 · Cited by 9,570
Show and tell: A neural image caption generator
Vinyals, O., Toshev, A., Bengio, S., & Erhan, D. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298935 · Cited by 6,318 · cited 1×
“Generative Visual Language Models (VLM) were first used for image/video captioning using recurrent networks [17, 68] and Transformer-based architectures [42, 56].”
MethodRepresentation Learning with Contrastive Predictive Coding
Oord, A. V. D., Li, Y., & Vinyals, O. (2018) · arXiv · doi:10.48550/arxiv.1807.03748 · Cited by 6,242 · cited 2×
“N ARRATOR generates new descriptions of the action taking place, potentially focusing on other objects being interacted with.”
BackgroundMethodUcf101: A dataset of 101 human actions classes from videos in the wild
Soomro, K., Zamir, A. R., & Shah, M. (2012) · arXiv · doi:10.48550/arxiv.1212.0402 · Cited by 4,575
Hmdb: a large video database for human motion recognition
Kuehne, H., Jhuang, H., Garrote, E., Poggio, T., & Serre, T. (2011) · 2011 International Conference on Computer Vision · doi:10.1109/iccv.2011.6126543 · Cited by 3,965
ViViT: A Video Vision Transformer
Arnab, A., Dehghani, M., Heigold, G., Sun, C., Lucic, M., & Schmid, C. (2021) · 2021 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.00676 · Cited by 2,767
ActivityNet: A large-scale video benchmark for human activity understanding
Heilbron, F. C., Escorcia, V., Ghanem, B., & Niebles, J. C. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298698 · Cited by 2,578
Hierarchical Text-Conditional Image Generation with CLIP Latents
Ramesh, A., Dhariwal, P., Nichol, A., Chu, C., & Chen, M. (2022) · arXiv · doi:10.48550/arxiv.2204.06125 · Cited by 2,511 · cited 1×
“Vision-language approaches [31, 49, 80] have pushed the state-of-the-art across a variety of tasks, including zero-shot classification [49], novel object detection [87], and even image generation [52].”
BackgroundViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks
Lu, J., Batra, D., Parikh, D., & Lee, S. (2019) · arXiv · doi:10.48550/arxiv.1908.02265 · Cited by 2,109
UNITER: UNiversal Image-TExt Representation Learning
Chen, Y.-C., Li, L., Yu, L., El Kholy, A., Ahmed, F., Gan, Z., Cheng, Y., & Liu, J. (2020) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-58577-8_7 · Cited by 2,055 · cited 1×
“Recently, different pretext tasks are proposed to learn a finer-grained association be-tween visual and textual modality, e.g . masked language modeling (MLM) [10, 41, 62] and captioning [16, 80].”
BackgroundScaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision
Jia, C., Yang, Y., Xia, Y., Chen, Y.-T., Parekh, Z., Pham, H., Le, Q. V., Sung, Y., Li, Z., & Duerig, T. (2021) · arXiv · doi:10.48550/arxiv.2102.05918 · Cited by 1,977
Is Space-Time Attention All You Need for Video Understanding?
Bertasius, G., Wang, H., & Torresani, L. (2021) · arXiv · doi:10.48550/arxiv.2102.05095 · Cited by 1,663
Flamingo: a Visual Language Model for Few-Shot Learning
Alayrac, J.-B., Donahue, J., Luc, P., Miech, A., Barr, I., Hasson, Y., Lenc, K., Mensch, A., Millican, K., Reynolds, M., et al. (2022) · arXiv · doi:10.48550/arxiv.2204.14198 · Cited by 1,555
The Curious Case of Neural Text Degeneration
Holtzman, A., Buys, J., Du, L., Forbes, M., & Choi, Y. (2019) · arXiv · doi:10.48550/arxiv.1904.09751 · Cited by 1,304
LAION-5B: An open large-scale dataset for training next generation image-text models
Schuhmann, C., Beaumont, R., Vencu, R., Gordon, C., Wightman, R., Cherti, M., Coombes, T., Katta, A., Mullis, C., Wortsman, M., et al. (2022) · arXiv · doi:10.48550/arxiv.2210.08402 · Cited by 1,022
HowTo100M: Learning a Text-Video Embedding by Watching Hundred Million Narrated Video Clips
Miech, A., Zhukov, D., Alayrac, J.-B., Tapaswi, M., Laptev, I., & Sivic, J. (2019) · 2019 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00272 · Cited by 986 · cited 9×
“Although prior work has leveraged automatic speech transcription on HowTo videos [45] to automatically extract clips paired with text from the speech, such datasets have relatively poor alignment between the visual and textual content (≤ 50%, cf .”
BackgroundMethodInfluentialVL-BERT: Pre-training of Generic Visual-Linguistic Representations
Su, W., Zhu, X., Cao, Y., Li, B., Lu, L., Wei, F., & Dai, J. (2019) · arXiv · doi:10.48550/arxiv.1908.08530 · Cited by 950 · cited 2×
“Recently, different pretext tasks are proposed to learn a finer-grained association be-tween visual and textual modality, e.g . masked language modeling (MLM) [10, 41, 62] and captioning [16, 80].”
BackgroundNeural Machine Translation of Rare Words with Subword Units
Sennrich, R., Haddow, B., & Birch, A. (2015) · arXiv · doi:10.48550/arxiv.1508.07909 · Cited by 950
Training Compute-Optimal Large Language Models
Hoffmann, J., Borgeaud, S., Mensch, A., Buchatskaya, E., Cai, T., Rutherford, E., Casas, D. D. L., Hendricks, L. A., Welbl, J., Clark, A., et al. (2022) · arXiv · doi:10.48550/arxiv.2203.15556 · Cited by 929
Zhai, X., Kolesnikov, A., Houlsby, N., & Beyer, L. (2022) · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52688.2022.01179 · Cited by 891
Ego4D: Around the World in 3,000 Hours of Egocentric Video
Grauman, K., Westbury, A., Byrne, E., Chavis, Z., Furnari, A., Girdhar, R., Hamburger, J., Jiang, H., Liu, M., Liu, X., et al. (2022) · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52688.2022.01842 · Cited by 630
Self-citationDetecting Twenty-Thousand Classes Using Image-Level Supervision
Zhou, X., Girdhar, R., Joulin, A., Krähenbühl, P., & Misra, I. (2022) · Lecture Notes in Computer Science · doi:10.1007/978-3-031-20077-9_21 · Cited by 564
Self-citationRescaling egocentric vision: Collection, pipeline and challenges for epic-kitchens-100
Damen, D., Doughty, H., Farinella, G. M., Furnari, A., Kazakos, E., Ma, J., Moltisanti, D., Munro, J., Perrett, T., Price, W., et al. (2022) · International Journal of Computer Vision · doi:10.1007/s11263-021-01531-2 · Cited by 400
Florence: A New Foundation Model for Computer Vision
Yuan, L., Chen, D., Chen, Y.-L., Codella, N., Dai, X., Gao, J., Hu, H., Huang, X., Li, B., Li, C., et al. (2021) · arXiv · doi:10.48550/arxiv.2111.11432 · Cited by 389 · cited 1×
“More recently, generative VLMs have unified multiple vision tasks [11, 89] by training multi-modal Transformers on visual-text pairs [30, 81].”
BackgroundMultimodal Few-Shot Learning with Frozen Language Models
Tsimpoukelli, M., Menick, J., Cabi, S., Eslami, S. M. A., Vinyals, O., & Hill, F. (2021) · arXiv · doi:10.48550/arxiv.2106.13884 · Cited by 355
Multiview Transformers for Video Recognition
Yan, S., Xiong, X., Arnab, A., Lu, Z., Zhang, M., Sun, C., & Schmid, C. (2022) · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52688.2022.00333 · Cited by 312
How to train your ViT? Data, Augmentation, and Regularization in Vision Transformers
Steiner, A., Kolesnikov, A., Zhai, X., Wightman, R., Uszkoreit, J., & Beyer, L. (2021) · arXiv · doi:10.48550/arxiv.2106.10270 · Cited by 292
Data Augmentation for Low-Resource Neural Machine Translation
Fadaee, M., Bisazza, A., & Monz, C. (2017) · Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers) · doi:10.18653/v1/p17-2090 · Cited by 266 · cited 1×
“Data augmentation techniques in NLP, including wordlevel replacement based on synonyms [72, 85] or nearestneighbor retrieval [19, 70], improve text classification accuracy.”
MethodFrozen CLIP Models are Efficient Video Learners
Lin, Z., Geng, S., Zhang, R., Gao, P., de Melo, G., Wang, X., Dai, J., Qiao, Y., & Li, H. (2022) · Lecture Notes in Computer Science · doi:10.1007/978-3-031-19833-5_23 · Cited by 213
Socratic Models: Composing Zero-Shot Multimodal Reasoning with Language
Zeng, A., Attarian, M., Ichter, B., Choromanski, K., Wong, A., Welker, S., Tombari, F., Purohit, A., Ryoo, M., Sindhwani, V., et al. (2022) · arXiv · doi:10.48550/arxiv.2204.00598 · Cited by 205
Frozen in Time: A Joint Video and Image Encoder for End-to-End Retrieval
Bain, M., Nagrani, A., Varol, G., & Zisserman, A. (2021) · 2021 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.00175 · Cited by 76
Cited by
Ego-Exo4D: Understanding Skilled Human Activity from First- and Third-Person Perspectives
Grauman, K., Westbury, A., Torresani, L., Kitani, K., Malik, J., Afouras, T., Ashutosh, K., Baiyya, V., Bansal, S., Boote, B., et al. (2024) · 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52733.2024.01834 · Cited by 182
VideoAgent: A Memory-augmented Multimodal Agent for Video Understanding
Fan, Y., Ma, X., Wu, R., Du, Y., Li, J., Gao, Z., & Li, Q. (2024) · arXiv · doi:10.48550/arxiv.2403.11481 · Cited by 60
Video ReCap: Recursive Captioning of Hour-Long Videos
Islam, M. M., Ho, N., Yang, X., Nagarajan, T., Torresani, L., & Bertasius, G. (2024) · 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52733.2024.01723 · Cited by 34
“Second, we inject trainable cross-attention layers [2, 67] Table S1.”
BackgroundMethodResultInfluentialRetrieval-Augmented Egocentric Video Captioning
Xu, J., Huang, Y., Hou, J., Chen, G., Zhang, Y., Feng, R., & Xie, W. (2024) · arXiv · doi:10.48550/arxiv.2401.00789 · Cited by 24
SALMONN: Towards Generic Hearing Abilities for Large Language Models
Tang, C., Yu, W., Sun, G., Chen, X., Tan, T., Li, W., Lu, L., Ma, Z., & Zhang, C. (2023) · arXiv · doi:10.48550/arxiv.2310.13289 · Cited by 67
“…type of input, such as image (Li et al., 2023a; Alayrac et al., 2022; Dai et al., 2023), silent video (Maaz et al., 2023; Chen et al., 2023b; Zhao et al., 2022), audio events (Gong et al., 2023b; Lyu et al., 2023) or speech (Chen et al., 2023a), or the encoders of multiple input types…”
Background
Metadata
- Authors
- Zhao, Y., Misra, I., Krähenbühl, P., & Girdhar, R.
- Venue
- 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
- Publisher
- IEEE
- Published
- 2023-06
- Pages
- 6586-6597
- ISSN
- 1063-6919 (ISSN-L)
- OpenAlex
- W4386076314
- Cited by
- 157
- References
- 38
- FWCI
- 17.85
- Type
- conference paper
- Language
- en
- Open access
- green
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.