The DOI matches its Crossref record; 57 of the 57 references it cites were found in a registry or an index.
MERLOT RESERVE: Neural Script Knowledge through Vision and Language and Sound
Open accessAbstract
As humans, we navigate a multimodal world, building a holistic understanding from all our senses. We introduce @MERLOT RESERVE, a model that represents videos jointly over time - through a new training objective that learns from audio, subtitles, and video frames. Given a video, we replace snippets of text and audio with a MASK token; the model learns by choosing the correct masked-out snippet. Our objective learns faster than alternatives, and performs well at scale: we pretrain on 20 million YouTube videos. Empirical results show that @MERLOT RESERVE learns strong multimodal representations. When finetuned, it sets state-of-the-art on Visual Commonsense Reasoning (VCR), TVQA, and Kinetics-600; outperforming prior work by 5%, 7%, and 1.5% respectively. Ablations show that these tasks benefit from audio pretraining - even VCR, a QA task centered around images (without sound). Moreover, our objective enables out-of-the-box prediction, revealing strong multimodal commonsense understanding. In a fully zero-shot setting, our model obtains competitive results on four video tasks, even outperforming supervised approaches on the recently proposed Situated Reasoning (STAR) benchmark. We analyze why audio enables better vision-language representations, suggesting significant opportunities for future research. We conclude by discussing ethical and societal implications of multimodal pretraining.
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
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2018) · arXiv · doi:10.48550/arxiv.1810.04805 · Cited by 73,173
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2019) · Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers) · doi:10.18653/v1/n19-1423 · Cited by 54,325
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
Situated Knowledges: The Science Question in Feminism and the Privilege of Partial Perspective
Haraway, D. (1988) · Feminist Studies · doi:10.2307/3178066 · Cited by 18,364
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
Decoupled Weight Decay Regularization
Loshchilov, I., & Hutter, F. (2017) · arXiv · doi:10.48550/arxiv.1711.05101 · Cited by 12,522
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
The origins of intelligence in children.
Piaget, J. (1952) · doi:10.1037/11494-000 · Cited by 10,687
Scaling Laws for Neural Language Models
Kaplan, J., McCandlish, S., Henighan, T., Brown, T. B., Chess, B., Child, R., Gray, S., Radford, A., Wu, J., & Amodei, D. (2020) · arXiv · doi:10.48550/arxiv.2001.08361 · Cited by 9,550 · cited 3×
“[65] Jared Kaplan, Sam McCandlish, Tom Henighan, Tom B Brown, Benjamin Chess, Rewon Child, Scott Gray, Alec Radford, Jeffrey Wu, and Dario Amodei.”
BackgroundMethodMultimodal Machine Learning: A Survey and Taxonomy
Baltrusaitis, T., Ahuja, C., & Morency, L.-P. (2019) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2018.2798607 · Cited by 5,018
ALBERT: A Lite BERT for Self-supervised Learning of Language Representations
Lan, Z., Chen, M., Goodman, S., Gimpel, K., Sharma, P., & Soricut, R. (2019) · arXiv · doi:10.48550/arxiv.1909.11942 · Cited by 4,308 · cited 3×
“[71] Zhenzhong Lan, Mingda Chen, Sebastian Goodman, Kevin Gimpel, Piyush Sharma, and Radu Soricut.”
BackgroundInfluentialEnergy and Policy Considerations for Deep Learning in NLP
Strubell, E., Ganesh, A., & McCallum, A. (2019) · Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics · doi:10.18653/v1/p19-1355 · Cited by 3,684
Big other: Surveillance Capitalism and the Prospects of an Information Civilization
Zuboff, S. (2015) · Journal of Information Technology · doi:10.1057/jit.2015.5 · Cited by 3,205
Audio Set: An ontology and human-labeled dataset for audio events
Gemmeke, J. F., Ellis, D. P. W., Freedman, D., Jansen, A., Lawrence, W., Moore, R. C., Plakal, M., & Ritter, M. (2017) · 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) · doi:10.1109/icassp.2017.7952261 · Cited by 3,134
VGGFace2: A Dataset for Recognising Faces across Pose and Age
Cao, Q., Shen, L., Xie, W., Parkhi, O. M., & Zisserman, A. (2018) · 2018 13th IEEE International Conference on Automatic Face & Gesture Recognition (FG 2018) · doi:10.1109/fg.2018.00020 · Cited by 3,032
On the Opportunities and Risks of Foundation Models
Bommasani, R., Hudson, D. A., Adeli, E., Altman, R., Arora, S., von Arx, S., Bernstein, M. S., Bohg, J., Bosselut, A., Brunskill, E., et al. (2021) · arXiv · doi:10.48550/arxiv.2108.07258 · Cited by 2,676
Unsupervised Visual Representation Learning by Context Prediction
Doersch, C., Gupta, A., & Efros, A. A. (2015) · 2015 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2015.167 · Cited by 2,629
Gebru, T., Morgenstern, J., Vecchione, B., Vaughan, J. W., Wallach, H., Daumé, H., & Crawford, K. (2018) · arXiv · doi:10.48550/arxiv.1803.09010 · Cited by 2,474
Gebru, T., Morgenstern, J., Vecchione, B., Vaughan, J. W., Wallach, H., III, H. D., & Crawford, K. (2021) · Communications of the ACM · doi:10.1145/3458723 · Cited by 2,469 · cited 2×
“For a Datasheet [41], please see the MERLOT paper [128].”
BackgroundMethodLXMERT: Learning Cross-Modality Encoder Representations from Transformers
Tan, H., & Bansal, M. (2019) · Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP) · doi:10.18653/v1/d19-1514 · Cited by 2,319
Making the V in VQA Matter: Elevating the Role of Image Understanding in Visual Question Answering
Goyal, Y., Khot, T., Summers-Stay, D., Batra, D., & Parikh, D. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.670 · Cited by 2,287
VoxCeleb: A Large-Scale Speaker Identification Dataset
Nagrani, A., Chung, J. S., & Zisserman, A. (2017) · Interspeech 2017 · doi:10.21437/interspeech.2017-950 · Cited by 2,210
ViLBERT: 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
Self-citationUNITER: 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
Scaling 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
RoFormer: Enhanced transformer with rotary position embedding
Su, J., Ahmed, M., Lu, Y., Pan, S., Bo, W., & Liu, Y. (2024) · Neurocomputing · doi:10.1016/j.neucom.2023.127063 · Cited by 1,957
RoFormer: Enhanced Transformer with Rotary Position Embedding
Su, J., Lu, Y., Pan, S., Murtadha, A., Wen, B., & Liu, Y. (2021) · arXiv · doi:10.48550/arxiv.2104.09864 · Cited by 1,952 · cited 3×
“[104] Jianlin Su, Yu Lu, Shengfeng Pan, Bo Wen, and Yunfeng Liu.”
BackgroundMethodSpanBERT: Improving Pre-training by Representing and Predicting Spans
Joshi, M., Chen, D., Liu, Y., Weld, D. S., Zettlemoyer, L., & Levy, O. (2020) · Transactions of the Association for Computational Linguistics · doi:10.1162/tacl_a_00300 · Cited by 1,827 · cited 4×
“We use past work in language modeling as a guide [63, 92] and wanted an average span length of around 5 tokens.”
BackgroundMethodInfluentialSpanBERT: Improving Pre-training by Representing and Predicting Spans
Joshi, M., Chen, D., Liu, Y., Weld, D. S., Zettlemoyer, L., & Levy, O. (2019) · arXiv · doi:10.48550/arxiv.1907.10529 · Cited by 1,827
Tacotron: towards end-to-end speech synthesis
Wang, Y., Skerry-Ryan, R. J., Stanton, D., Wu, Y., Weiss, R. J., Jaitly, N., Yang, Z., Xiao, Y., Chen, Z., Bengio, S., et al. (2017) · Interspeech 2017 · doi:10.21437/interspeech.2017-1452 · Cited by 1,746 · cited 2×
“We used a small number of mel spectrogram bins (64) because we found that at that threshold, we could reconstruct the original sequence at an acceptable level using the Griffin-Lim algorithm, [52] which itself might be a lower bound on quality as neural methods trained for this purpose have been shown to do better [11…”
BackgroundMethodIs 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
VisualBERT: A Simple and Performant Baseline for Vision and Language
Li, L. H., Yatskar, M., Yin, D., Hsieh, C.-J., & Chang, K.-W. (2019) · arXiv · doi:10.48550/arxiv.1908.03557 · Cited by 1,198 · cited 2×
“[76] Liunian Harold Li, Mark Yatskar, Da Yin, Cho-Jui Hsieh, and Kai-Wei Chang.”
MethodAST: Audio Spectrogram Transformer
Gong, Y., Chung, Y.-A., & Glass, J. (2021) · Interspeech 2021 · doi:10.21437/interspeech.2021-698 · Cited by 1,159
Climbing towards NLU: On Meaning, Form, and Understanding in the Age of Data
Bender, E. M., & Koller, A. (2020) · Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics · doi:10.18653/v1/2020.acl-main.463 · Cited by 1,082 · cited 1×
“One of the root causes of such bias is learning objectives that encourage memorization of surface level cooccurences, rather than truly causal factors [55, 9, 117].”
BackgroundBig Transfer (BiT): General Visual Representation Learning
Kolesnikov, A., Beyer, L., Zhai, X., Puigcerver, J., Yung, J., Gelly, S., & Houlsby, N. (2019) · arXiv · doi:10.48550/arxiv.1912.11370 · Cited by 1,039
Big Transfer (BiT): General Visual Representation Learning
Kolesnikov, A., Beyer, L., Zhai, X., Puigcerver, J., Yung, J., Gelly, S., & Houlsby, N. (2020) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-58558-7_29 · Cited by 1,039 · cited 2×
“Recent prior work on static images that demonstrates empirical improvements by increasing dataset size – all the way up to JFT-3B [69, 34, 91, 128].”
BackgroundHowTo100M: 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 3×
“Weplan to release only video IDs for download, following prior work [1, 83].”
BackgroundMethodNetworked privacy: How teenagers negotiate context in social media
Marwick, A. E., & boyd, D. (2014) · New Media & Society · doi:10.1177/1461444814543995 · Cited by 954 · cited 1×
“We took inspiration from Marwick and Boyd [82]’s framework of networked privacy, which posits that users posting public videos might encode private information – enough so that their intended viewership (friends, possibly) can catch the gist, but not enough so as to leak private details like phone numbers to the world.”
MethodMen Also Like Shopping: Reducing Gender Bias Amplification using Corpus-level Constraints
Zhao, J., Wang, T., Yatskar, M., Ordonez, V., & Chang, K.-W. (2017) · Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/d17-1323 · Cited by 829 · cited 3×
“[131] Jieyu Zhao, Tianlu Wang, Mark Yatskar, Vicente Ordonez, and Kai-Wei Chang.”
BackgroundMethodFrom Recognition to Cognition: Visual Commonsense Reasoning
Zellers, R., Bisk, Y., Farhadi, A., & Choi, Y. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2019.00688 · Cited by 769
Self-citationExtracting Training Data from Large Language Models
Carlini, N., Tramer, F., Wallace, E., Jagielski, M., Herbert-Voss, A., Lee, K., Roberts, A., Brown, T., Song, D., Erlingsson, U., et al. (2020) · arXiv · doi:10.48550/arxiv.2012.07805 · Cited by 727
RealToxicityPrompts: Evaluating Neural Toxic Degeneration in Language Models
Gehman, S., Gururangan, S., Sap, M., Choi, Y., & Smith, N. A. (2020) · Findings of the Association for Computational Linguistics: EMNLP 2020 · doi:10.18653/v1/2020.findings-emnlp.301 · Cited by 693
Self-citationThe Development of Embodied Cognition: Six Lessons from Babies
Smith, L., & Gasser, M. (2005) · Artificial Life · doi:10.1162/1064546053278973 · Cited by 597 · cited 2×
“Reentry has been hypothesized by developmental psychologists to be crucial for how we as humans learn visual and world knowledge, much of it without need for an explicit teacher [88, 35, 19, 100].”
BackgroundAuditing radicalization pathways on YouTube
Ribeiro, M. H., Ottoni, R., West, R., Almeida, V. A. F., & Meira, W. (2020) · Proceedings of the 2020 Conference on Fairness, Accountability, and Transparency · doi:10.1145/3351095.3372879 · Cited by 580
Defending Against Neural Fake News
Zellers, R., Holtzman, A., Rashkin, H., Bisk, Y., Farhadi, A., Roesner, F., & Choi, Y. (2019) · arXiv · doi:10.48550/arxiv.1905.12616 · Cited by 569
Self-citationTVQA: Localized, Compositional Video Question Answering
Lei, J., Yu, L., Bansal, M., & Berg, T. (2018) · Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/d18-1167 · Cited by 541 · cited 4×
“[74] Jie Lei, Licheng Yu, Mohit Bansal, and Tamara L Berg.”
BackgroundMethodInfluentialCarbon Emissions and Large Neural Network Training
Patterson, D., Gonzalez, J., Le, Q., Liang, C., Munguia, L.-M., Rothchild, D., So, D., Texier, M., & Dean, J. (2021) · arXiv · doi:10.48550/arxiv.2104.10350 · Cited by 486
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
Don’t Take the Easy Way Out: Ensemble Based Methods for Avoiding Known Dataset Biases
Clark, C., Yatskar, M., & Zettlemoyer, L. (2019) · Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP) · doi:10.18653/v1/d19-1418 · Cited by 381
Gender and Dialect Bias in YouTube’s Automatic Captions
Tatman, R. (2017) · Proceedings of the First ACL Workshop on Ethics in Natural Language Processing · doi:10.18653/v1/w17-1606 · Cited by 338
Audioclip: Extending Clip to Image, Text and Audio
Guzhov, A., Raue, F., Hees, J., & Dengel, A. (2022) · ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) · doi:10.1109/icassp43922.2022.9747631 · Cited by 330
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
A Short Note about Kinetics-600
Carreira, J., Noland, E., Banki-Horvath, A., Hillier, C., & Zisserman, A. (2018) · arXiv · doi:10.48550/arxiv.1808.01340 · Cited by 270
Anxiety, panic and self-optimization: Inequalities and the YouTube algorithm
Bishop, S. (2018) · Convergence: The International Journal of Research into New Media Technologies · doi:10.1177/1354856517736978 · Cited by 253
The limits of transparency: Data brokers and commodification
Crain, M. (2018) · New Media & Society · doi:10.1177/1461444816657096 · Cited by 237
Does my multimodal model learn cross-modal interactions? It’s harder to tell than you might think!
Hessel, J., & Lee, L. (2020) · Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2020.emnlp-main.62 · Cited by 57
Self-citation
Cited by
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) · Advances in Neural Information Processing Systems 35 · doi:10.52202/068431-1723 · Cited by 966
“In particular, BERT [23] inspired a large body of vision-language work [16, 28, 29, 38, 59, 61, 66, 101, 106, 107, 109, 118, 121, 142, 143, 151].”
BackgroundMethodObjaverse: A Universe of Annotated 3D Objects
Deitke, M., Schwenk, D., Salvador, J., Weihs, L., Michel, O., VanderBilt, E., Schmidt, L., Ehsanit, K., Kembhavi, A., & Farhadi, A. (2023) · 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52729.2023.01263 · Cited by 725
“Language corpora on the web led to large language models like GPT-3 [4]; paired image and text datasets like Conceptual Captions [63] led to vision-and-language pretrained models like VilBERT [42]; YouTube video datasets led to video capable models like Merlot-Reserve [82]; and massive multimodal datasets like WebImag…”
MethodSelf-citationVLP: A Survey on Vision-language Pre-training
Chen, F.-L., Zhang, D.-Z., Han, M.-L., Chen, X.-Y., Shi, J., Xu, S., & Xu, B. (2023) · Machine Intelligence Research · doi:10.1007/s11633-022-1369-5 · Cited by 279
Vid2Seq: Large-Scale Pretraining of a Visual Language Model for Dense Video Captioning
Yang, A., Nagrani, A., Seo, P. H., Miech, A., Pont-Tuset, J., Laptev, I., Sivic, J., & Schmid, C. (2023) · 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52729.2023.01032 · Cited by 254
Vision-Language Pre-Training: Basics, Recent Advances, and Future Trends
Gan, Z., Li, L., Li, C., Wang, L., Liu, Z., & Gao, J. (2022) · Foundations and Trends® in Computer Graphics and Vision · doi:10.1561/0600000105 · Cited by 155
Metadata
- Authors
- Zellers, R., Lu, J., Lu, X., Yu, Y., Zhao, Y., Salehi, M., Kusupati, A., Hessel, J., Farhadi, A., & Choi, Y.
- Venue
- 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
- Publisher
- IEEE
- Published
- 2022-06
- Pages
- 16354-16366
- ISSN
- 1063-6919 (ISSN-L)
- OpenAlex
- W4221154653
- Cited by
- 160
- References
- 57
- FWCI
- 13.62
- 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.