The DOI matches its Crossref record; 106 of the 111 references it cites were found in a registry or an index.
Multiscale Vision Transformers
Open accessAbstract
We present Multiscale Vision Transformers (MViT) for video and image recognition, by connecting the seminal idea of multiscale feature hierarchies with transformer models. Multiscale Transformers have several channel-resolution scale stages. Starting from the input resolution and a small channel dimension, the stages hierarchically expand the channel capacity while reducing the spatial resolution. This creates a multiscale pyramid of features with early layers operating at high spatial resolution to model simple low-level visual information, and deeper layers at spatially coarse, but complex, high-dimensional features. We evaluate this fundamental architectural prior for modeling the dense nature of visual signals for a variety of video recognition tasks where it outperforms concurrent vision transformers that rely on large scale external pre-training and are 5-10× more costly in computation and parameters. We further remove the temporal dimension and apply our model for image classification where it outperforms prior work on vision transformers. Code is available at: https://github.com/facebookresearch/SlowFast.
Overview
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
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 · cited 2×
“As in original ViT [25], we use residual connections [45] and Layer Normalization (LN) [2] in the pre-normalization configuration that applies LN at the beginning of the residual function, and our MLPs consist of two linear layers with GELU activation [48], where the first layer expands the dimension from D to 4D, and…”
MethodResultVaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, L., & Polosukhin, I. (2017) · arXiv · doi:10.48550/arxiv.1706.03762 · Cited by 120,404 · cited 6×
“In contrast to original Multi Head Attention (MHA) operators [98], where the channel dimension and the spatiotemporal resolution remains fixed, MHPA pools the sequence of latent tensors to reduce the sequence length (resolution) of the attended input.”
BackgroundMethodInfluentialVery Deep Convolutional Networks for Large-Scale Image Recognition
Simonyan, K., & Zisserman, A. (2014) · arXiv · doi:10.48550/arxiv.1409.1556 · Cited by 114,148 · cited 1×
“Incorporating downsampling, shift invariance, and shared weights, ConvNets are de-facto standard backbones for computer vision tasks for image [65, 62, 88, 90, 46, 12, 15, 34, 93, 81, 41] and video [87, 31, 11, 79, 69, 106, 96, 30, 105, 35, 29, 117, 57].”
BackgroundImageNet classification with deep convolutional neural networks
Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2017) · Communications of the ACM · doi:10.1145/3065386 · Cited by 112,155 · cited 1×
“Incorporating downsampling, shift invariance, and shared weights, ConvNets are de-facto standard backbones for computer vision tasks for image [70, 67, 94, 96, 51, 15, 18, 39, 99, 87, 46] and video [93, 36, 14, 85, 74, 112, 102, 34, 111, 40, 33, 123, 62].”
BackgroundFaster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
Ren, S., He, K., Girshick, R., & Sun, J. (2017) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2016.2577031 · Cited by 73,472
Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
Ren, S., He, K., Girshick, R., & Sun, J. (2015) · arXiv · doi:10.48550/arxiv.1506.01497 · Cited by 70,812
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
Going deeper with convolutions
Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., Erhan, D., Vanhoucke, V., & Rabinovich, A. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298594 · Cited by 48,562
Swin Transformer: Hierarchical Vision Transformer using Shifted Windows
Liu, Z., Lin, Y., Cao, Y., Hu, H., Wei, Y., Zhang, Z., Lin, S., & Guo, B. (2021) · 2021 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.00986 · Cited by 35,534 · cited 1×
“Finally, compared to the best model of concurrent Swin [79] (which was designed for image recognition), MViT has +0.”
ResultRethinking the Inception Architecture for Computer Vision
Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., & Wojna, Z. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.308 · Cited by 32,138
Research works printed but not linked: 11
- gao, 2019, Res2net: A new multi-scale backbone architecture, IEEE PAMI
- fan, 2020, Pyslowfast
- feichtenhofer, 2019, SlowFast networks for video recognition in ActivityNet challenge 2019
- 10.1109/CVPR.2009.5206848 · DOI · Paper page
- 10.1109/CVPR.2019.00033 · DOI
- hang, 2020, ResNeSt Split-Attention Networks
- 10.1109/ICCV.2019.00718 · DOI
- 10.1109/CVPR.2015.7298594 · DOI · Paper page
- carion, 2020, Endto-end object detection with transformers, Proc ECCV, 213
- loshchilov, 2018, Fixing weight decay regularization in adam
- qiu, 2017, Learning spatiotemporal representation with pseudo-3d residual networks, Proc ICCV
Cited by
Sorted by citations
Liu, Z., Mao, H., Wu, C.-Y., Feichtenhofer, C., Darrell, T., & Xie, S. (2022) · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52688.2022.01167 · Cited by 8,494
“The original ViT [20] first studied a hybrid config-uration, and a large body of follow-up works focused on reintroducing convolutional priors to ViT, either in an explicit [15,16,21,82,86,88] or implicit [45] fashion.”
BackgroundSelf-citationHan (2023) · doi:10.1109/tpami.2022.3152247 · Cited by 4,682
“transformer models [232], [148], [209], [61], [279], [167] including PVT [232], HVT [168], Swin Transformer [148] and PiT [92].”
MethodTransformers in Vision: A Survey
Khan, S., Naseer, M., Hayat, M., Zamir, S. W., Khan, F. S., & Shah, M. (2022) · ACM Computing Surveys · doi:10.1145/3505244 · Cited by 3,595
“Numerous methods have been proposed that make special design choices to perform self-attention more ‘eiciently’, for instance employing pooling/downsampling in self-attention [61, 209, 221], local window-based attention [138, 201], axial-attention [55, 83], low-rank projection attention [192, 208, 225], kernelizable a…”
BackgroundMethodLiu, Z., Ning, J., Cao, Y., Wei, Y., Zhang, Z., Lin, S., & Hu, H. (2022) · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52688.2022.00320 · Cited by 2,294
“The great success of image Transformers has led to investigation of Transformer-based architectures for video-based recognition tasks [29, 1, 3, 9, 25].”
BackgroundInfluentialConvNeXt V2: Co-designing and Scaling ConvNets with Masked Autoencoders
Woo, S., Debnath, S., Hu, R., Chen, X., Liu, Z., Kweon, I. S., & Xie, S. (2023) · 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52729.2023.01548 · Cited by 1,791
“We compare our results to the state-of-the-art architecture designs, including convolutionbased [52, 64], transformer-based [22], and hybrid designs [20,66].”
Result(2022) · doi:10.1007/978-3-031-20053-3_27 · Cited by 1,060
Self-citationExploring Plain Vision Transformer Backbones for Object Detection
Li, Y., Mao, H., Girshick, R., & He, K. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-20077-9_17 · Cited by 1,027
Self-citationMViTv2: Improved Multiscale Vision Transformers for Classification and Detection
Li, Y., Wu, C.-Y., Fan, H., Mangalam, K., Xiong, B., Malik, J., & Feichtenhofer, C. (2022) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52688.2022.00476 · Cited by 909
“The latter fuels Multiscale Vision Transformers (MViT) [21], an architecture that extends ViT in a simple way: instead of having a fixed resolution throughout the network, it has a feature hierarchy with multiple stages starting from high-resolution to low-resolution.”
BackgroundMethodInfluentialSelf-citationBeyond Self-Attention: External Attention Using Two Linear Layers for Visual Tasks
Guo, M.-H., Liu, Z.-N., Mu, T., & Hu, S. (2022) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2022.3211006 · Cited by 703
“Subsequently, transformer methods have been successfully applied tomanyvisual tasks, including image classification [12], [31], [32], [33], object detection [34], lower-level vision [35], semantic segmentation [36], tracking [37], video instance segmentation [38], image generation [39],multimodal learning [40], Fig.”
MethodUniFormer: Unifying Convolution and Self-Attention for Visual Recognition
Li, K., Wang, Y., Zhang, J., Gao, P., Song, G., Liu, Y., Li, H., & Qiao, Y. (2023) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2023.3282631 · Cited by 682
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
“[63] Haoqi Fan, Bo Xiong, Karttikeya Mangalam, Yanghao Li, Zhicheng Yan, Jitendra Malik, and Christoph Feichtenhofer.”
BackgroundSelf-citationScaling Vision Transformers to Gigapixel Images via Hierarchical Self-Supervised Learning
Chen, R. J., Chen, C., Li, Y., Chen, T. Y., Trister, A. D., Krishnan, R. G., & Mahmood, F. (2022) · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52688.2022.01567 · Cited by 621
“- Swin, ViL, TNT, PVT, MViT) in addressing the varying scale / aspect ratios of visual tokens [27, 31, 51, 72, 81].”
BackgroundSelf-citationEarly Convolutions Help Transformers See BetterPreprint
Xiao, T., Singh, M., Mintun, E., Darrell, T., Dollár, P., & Girshick, R. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2106.14881 · Cited by 596
“Dominant themes include multi-scale networks [14, 17, 25, 45, 50], increasing depth [42], and locality priors [5, 9, 17, 47, 49].”
BackgroundMasked Feature Prediction for Self-Supervised Visual Pre-Training
Wei, C., Fan, H., Xie, S., Wu, C.-Y., Yuille, A., & Feichtenhofer, C. (2022) · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52688.2022.01426 · Cited by 587
“The original MViT in [31] is termed as MViTv1.”
BackgroundMethodInfluentialSelf-citationGenerative artificial intelligence: a systematic review and applications
Sengar, S. S., Hasan, A. B., Kumar, S., & Carroll, F. (2024) · Multimedia Tools and Applications · doi:10.1007/s11042-024-20016-1 · Cited by 763
GroupViT: Semantic Segmentation Emerges from Text Supervision
Xu, J., Mello, S. D., Liu, S., Byeon, W., Breuel, T. M., Kautz, J., & Wang, X. (2022) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52688.2022.01760 · Cited by 518
“Inspired by the success of Transformers in NLP [20,76], the Vision Transformer (ViT) [22] was recently proposed and has been successfully applied to multiple computer vision tasks, including image classification [44, 72, 73, 86], object detection [44, 79, 88], semantic segmentation [44, 82, 91] and action recognition…”
MethodActionFormer: Localizing Moments of Actions with Transformers
Zhang, C.-L., Wu, J., & Li, Y. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-19772-7_29 · Cited by 514
Self-citationVideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training
Tong, Z., Song, Y., Wang, J., & Wang, L. (2022) · arXiv · doi:10.48550/arxiv.2203.12602 · Cited by 909
SimVP: Simpler yet Better Video Prediction
Gao, Z., Tan, C., Wu, L., & Li, S. Z. (2022) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52688.2022.00317 · Cited by 466
Touvron, H., Cord, M., & Jégou, H. (2022) · Lecture Notes in Computer Science · doi:10.1007/978-3-031-20053-3_30 · Cited by 409
DilateFormer: Multi-Scale Dilated Transformer for Visual Recognition
Jiao, J., Tang, Y.-M., Lin, K.-Y., Gao, Y., Ma, A. J., Wang, Y., & Zheng, W. (2023) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2023.3243616 · Cited by 417
“[35], [41], [51], [53], [70], [93], [114] is beneficial for dense prediction tasks such as object detection, instance and semantic segmentation, recent works [21], [23], [32], [38], [42], [54], [58], [66], [77], [78], [95], [104] introduce multi-scale modeling capability by using a pyramid structure to design their tr…”
BackgroundLi, J., Chen, J., Tang, Y., Wang, C., Landman, B. A., & Zhou, S. K. (2023) · Medical Image Analysis · doi:10.1016/j.media.2023.102762 · Cited by 454
MPViT: Multi-Path Vision Transformer for Dense Prediction
Lee, Y., Kim, J., Willette, J., & Hwang, S. J. (2022) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52688.2022.00714 · Cited by 401
“classification [17, 37, 50, 51, 57, 58, 65, 67], object detection [5, 12, 74], and semantic segmentation [54, 63] to temporal tasks such as video classification [1, 3, 18] and object tracking [7, 41, 56].”
MethodExpanding Language-Image Pretrained Models for General Video Recognition
Ni, B., Peng, H., Chen, M., Zhang, S., Meng, G., Fu, J., Xiang, S., & Ling, H. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-19772-7_1 · Cited by 401
VideoMamba: State Space Model for Efficient Video Understanding
Li, K., Li, X., Wang, Y., He, Y., Wang, Y., Wang, L., & Qiao, Y. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-73347-5_14 · Cited by 500
Edgenext: Efficiently amalgamated CNN-transformer architecture for mobile vision applications
Maaz, M., Shaker, A., Cholakkal, H., Khan, S., Zamir, S. W., Anwer, R. M., & Shahbaz Khan, F. (2023) · Lecture Notes in Computer Science · doi:10.1007/978-3-031-25082-8_1 · Cited by 407
PhysFormer: Facial Video-based Physiological Measurement with Temporal Difference Transformer
Yu, Z., Shen, Y., Shi, J., Zhao, H., Torr, P. H. S., & Zhao, G. (2022) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52688.2022.00415 · Cited by 341
“Some works [20, 41] conduct temporal contextual modeling with transformer based on single-frame features from pretrained 2D networks, while other works [1, 3, 4, 15,38] mine the spatio-temporal attentions via video trans-former directly.”
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
“In practice, due to the limited amount of training data, applying similar multiscale processing in transformers [11, 21, 44, 74] to reduce complexity of the model has proven to be effective.”
BackgroundMethodInfluentialP2T: Pyramid Pooling Transformer for Scene Understanding
Wu, Y.-H., Liu, Y., Zhan, X., & Cheng, M. (2022) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2022.3202765 · Cited by 334
“Unfortunately, most of recent development on transformer focuses on improving image classification on ImageNet [1] without considering this problem [19]–[22].”
BackgroundVOLO: Vision Outlooker for Visual Recognition
Yuan, L., Hou, Q., Jiang, Z., Feng, J., & Yan, S. (2022) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2022.3206108 · Cited by 350
SwiftFormer: Efficient Additive Attention for Transformer-based Real-time Mobile Vision Applications
Shaker, A., Maaz, M., Rasheed, H., Khan, S., Yang, M., & Khan, F. S. (2023) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51070.2023.01598 · Cited by 311
“These include computing attention across feature dimensions to implicitly model the global context [29], computing attention within local windows [24], pooling spatial features before applying self-attention [9], and sparsely attending to a fixed number of tokens [34], to name a few.”
BackgroundMethodEdgeViTs: Competing Light-Weight CNNs on Mobile Devices with Vision Transformers
Pan, J., Bulat, A., Tan, F., Zhu, X., Dudziak, Ł., Li, H., Tzimiropoulos, G., & Martínez, B. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-20083-0_18 · Cited by 316
EfficientSAM: Leveraged Masked Image Pretraining for Efficient Segment Anything
Xiong, Y., Varadarajan, B., Wu, L., Xiang, X., Xiao, F., Zhu, C., Dai, X., Wang, D., Sun, F., Iandola, F., et al. (2024) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52733.2024.01525 · Cited by 356
“ViTs [19] have achieved impressive performance in vision applications[5, 20, 26, 34, 39, 44].”
BackgroundViTAEv2: Vision Transformer Advanced by Exploring Inductive Bias for Image Recognition and Beyond
Zhang, Q., Xu, Y., Zhang, J., & Tao, D. (2023) · International Journal of Computer Vision · doi:10.1007/s11263-022-01739-w · Cited by 486
Humans in 4D: Reconstructing and Tracking Humans with Transformers
Goel, S., Pavlakos, G., Rajasegaran, J., Kanazawa, A., & Malik, J. (2023) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51070.2023.01358 · Cited by 339
“Canonical examples in this category include SlowFast [18] and MViT [16].”
BackgroundSelf-citationKim, J., Kim, H., Kim, H., Lee, D., & Yoon, S. (2025) · Artificial Intelligence Review · doi:10.1007/s10462-025-11223-9 · Cited by 389
CTNet: Context-Based Tandem Network for Semantic Segmentation
Li, Z., Sun, Y., Zhang, L., & Tang, J. (2021) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2021.3132068 · Cited by 273
“Recently, some methods [41], [42], [43], [44] apply the transformer idea to the backbone network for improving the network semantic space and the segmentation performance.”
MethodMulti-Scale High-Resolution Vision Transformer for Semantic Segmentation
Gu, J., Kwon, H., Wang, D., Ye, W., Li, M., Chen, Y., Lai, L., Chandra, V., & Pan, D. Z. (2022) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52688.2022.01178 · Cited by 282
“Several multi-scale ViTs adopt hierarchical architectures to generate progressively down-sampled pyramid features [3, 5, 11, 13, 28, 33].”
BackgroundAdaViT: Adaptive Vision Transformers for Efficient Image Recognition
Meng, L., Li, H., Chen, B.-C., Lan, S., Wu, Z., Jiang, Y.-G., & Lim, S.-N. (2022) · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52688.2022.01199 · Cited by 262
“3.3.”
BackgroundMethodInfluentialFAST-VQA: Efficient End-to-End Video Quality Assessment with Fragment Sampling
Wu, H., Chen, C., Hou, J., Liao, L., Wang, A., Sun, W., Yan, Q., & Lin, W. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-20068-7_31 · Cited by 286
Wave-ViT: Unifying Wavelet and Transformers for Visual Representation Learning
Yao, T., Pan, Y., Li, Y., Ngo, C., & Mei, T. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-19806-9_19 · Cited by 284
Self-citationScale-MAE: A Scale-Aware Masked Autoencoder for Multiscale Geospatial Representation Learning
Reed, C., Gupta, R., Li, S., Brockman, S., Funk, C., Clipp, B., Keutzer, K., Candido, S., Uyttendaele, M., & Darrell, T. (2023) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51070.2023.00378 · Cited by 353
“Recently, this multiscale idea has been extended to vision transformers by [18], who show that this architecture improves various video recognition and image classification tasks.”
BackgroundA systematic review of deep learning techniques for plant diseases
Paçal, İ., Kunduracıoğlu, İ., Alma, M. H., Deveci, M., Kadry, S., Nedoma, J., Slaný, V., & Martínek, R. (2024) · Artificial Intelligence Review · doi:10.1007/s10462-024-10944-7 · Cited by 353
Transformer-Based Visual Segmentation: A Survey
Li, X., Ding, H., Yuan, H., Zhang, W., Pang, J., Cheng, G., Chen, K., Liu, Z., & Loy, C. C. (2024) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2024.3434373 · Cited by 305
“MViT-V1 [131] introduces the multiscale feature representation and pooling strategies to reduce the computation cost in MHSA.”
MethodNascimento, E. G. S., Melo, T. A. C., & Moreira, D. M. (2023) · Energy · doi:10.1016/j.energy.2023.127678 · Cited by 223
Frozen 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
Anticipative Video Transformer
Girdhar, R., & Grauman, K. L. (2021) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.01325 · Cited by 237
“In contrast, AVT is an end-to-end transformer architecture for video—to our knowledge the first (concurrent with [4, 7, 19, 52, 63]).”
BackgroundBEVT: BERT Pretraining of Video Transformers
Wang, R., Chen, D., Wu, Z., Chen, Y., Dai, X., Liu, M., Jiang, Y.-G., Zhou, L., & Yuan, L. (2022) · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52688.2022.01432 · Cited by 234
“Motivated by the impressive performance of transformers that are able to capture long-range dependencies in a wide range of natural language processing tasks, there is a growing interest in using trans-2 formers for computer vision tasks [19, 20, 36, 43, 49, 69].”
BackgroundOmnivore: A Single Model for Many Visual Modalities
Girdhar, R., Singh, M., Ravi, N., van der Maaten, L. J. P., Joulin, A., & Misra, I. (2022) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52688.2022.01563 · Cited by 235
“While O MNIVORE can use any vision transformer architecture [21, 24] to process the patch embeddings, we use the Swin transformer architecture [51] as our base model given its strong performance on image and video tasks.”
BackgroundMethodAdaptive Token Sampling for Efficient Vision Transformers
Fayyaz, M., Koohpayegani, S. A., Jafari, F. R., Sengupta, S., Joze, H. R. V., Sommerlade, E., Pirsiavash, H., & Gall, J. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-20083-0_24 · Cited by 219
S2-MLP: Spatial-Shift MLP Architecture for Vision
Yu, T., Li, X., Cai, Y., Sun, M., & Li, P. (2022) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv51458.2022.00367 · Cited by 231
Conformer: Local Features Coupling Global Representations for Recognition and Detection
Peng, Z., Guo, Z., Huang, W., Wang, Y., Xie, L., Jiao, J., Tian, Q. C., & Ye, Q. (2023) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2023.3243048 · Cited by 194
“TheMultiscaleTransformer[39]andPyramidTransformer[40] createdfeaturepyramidswithearlylayersoperatingathighspa-tialresolutiontomodelsimplelow-levelvisualinformation,and deeperlayersatspatiallycoarse,butcomplex,high-dimensional features.”
Yao, T., Li, Y., Pan, Y., Wang, Y., Zhang, X.-P. S., & Mei, T. (2023) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2023.3268446 · Cited by 194
“The advances [8], [28], [30] introduce spatial reduction attention by using the down-sampling operations (e.”
BackgroundMethodInfluentialSelf-citationSelva, J., Johansen, A. S., Escalera, S., Nasrollahi, K., Moeslund, T. B., & Clapés, A. (2023) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2023.3243465 · Cited by 192
“For instance, [7], [9], [30] adopted an encoder-only architecture (along with the inclusion of [CLS] ) for video classification following [5].”
BackgroundMethodInfluentialMeMViT: Memory-Augmented Multiscale Vision Transformer for Efficient Long-Term Video Recognition
Wu, C.-Y., Li, Y., Mangalam, K., Fan, H., Xiong, B., Malik, J., & Feichtenhofer, C. (2022) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52688.2022.01322 · Cited by 201
“More recently, methods built upon the Transformer [74] architecture (the vision transformers) have been shown promising results [2,3,22,51,54].”
BackgroundMethodInfluentialSelf-citationSpatio-temporal Relation Modeling for Few-shot Action Recognition
Thatipelli, A., Narayan, S., Khan, S. H., Anwer, R. M., Khan, F. S., & Ghanem, B. (2022) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52688.2022.01933 · Cited by 169
“9% over TRX on SSv2, when employing 3D ResNet50 and MViT [9] backbones.”
MethodInfluentialKunduracıoğlu, İ., & Paçal, İ. (2024) · Journal of Plant Diseases and Protection · doi:10.1007/s41348-024-00896-z · Cited by 195
“Multiscale vision transformers (MViT) are transformer structures introduced by Fan et al. (2021) for modeling visual data such as images and videos.”
Lightweight transformer image feature extraction network
Zheng, W., Lu, S., Yang, Y., Yin, Z., & Yin, L. (2024) · PeerJ Computer Science · doi:10.7717/peerj-cs.1755 · Cited by 167
“The design concept of MViT ( Fan et al., 2021 ) proposed by Facebook in April 2021 is similar to that of PVT, and improved MViT was further proposed in December 2021 ( Li et al., 2022a ).”
A Survey on Efficient Vision Transformers: Algorithms, Techniques, and Performance Benchmarking
Papa, L., Russo, P., Amerini, I., & Zhou, L. (2024) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2024.3392941 · Cited by 200
“Li et al. [33] (2022) propose MViTv2, an improvement of the previously proposed MViT backbone by Haoqi Fan et al. [34] (2021).”
BackgroundSelf-supervised learning for videos: A survey
Schiappa, M. C., Rawat, Y. S., & Shah, M. (2023) · ACM Computing Surveys · doi:10.1145/3577925 · Cited by 155
“1 MaskFeat [188] Generative MAE MViT [41] Kinetics 74.”
BackgroundMethodShen, W., Peng, Z., Wang, X., Wang, H., Cen, J., Jiang, D., Xie, L., Yang, X., & Tian, Q. C. (2023) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2023.3246102 · Cited by 154
“The emergence of vision transformer (ViT) [167] and its variants [168], [169], [170], [171]”
BackgroundUnmasked Teacher: Towards Training-Efficient Video Foundation Models
Li, K., Wang, Y., Li, Y., Wang, Y., He, Y., Wang, L., & Qiao, Y. (2023) · 2023 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51070.2023.01826 · Cited by 143
Self-citationA Survey on Video Action Recognition in Sports: Datasets, Methods and Applications
Wu, F. L., Wang, Q., Bian, J., Ding, N., Lu, F., Cheng, J. S., Dou, D., & Xiong, H. (2022) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2022.3232034 · Cited by 167
Yu, Z., Shen, Y., Shi, J., Zhao, H., Cui, Y., Zhang, J., Torr, P. H. S., & Zhao, G. (2023) · International Journal of Computer Vision · doi:10.1007/s11263-023-01758-1 · Cited by 149
“, 2021) conduct temporal contextual modeling with transformer based on single-frame features from pretrained 2D networks, while other works (Arnab et al., 2021; Bertasius et al., 2021; Bulat et al., 2021; Fan et al., 2021; Liu et al., 2021e) mine the spatio-temporal attentions via video transformer directly.”
BackgroundMethodInfluentialKVT: k-NN Attention for Boosting Vision Transformers
Wang, P., Wang, X., Wang, F., Lin, M., Chang, S., Li, H., & Jin, R. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-20053-3_17 · Cited by 142
Video Frame Interpolation Transformer
Shi, Z., Xu, X., Liu, X., Chen, J., & Yang, M. (2022) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52688.2022.01696 · Cited by 135
“To enable Transformer-based upsampling, we extend the idea in [12] by upsampling the query with bilinear interpolation.”
MethodActive Learning by Feature Mixing
Parvaneh, A., Abbasnejad, E., Teney, D., Haffari, R., van den Hengel, A., & Shi, Q. (2022) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52688.2022.01192 · Cited by 138
“In addition, our approach performs significantly better that its counterparts for video classification using transformers [14].”
MethodRecurring the Transformer for Video Action Recognition
Yang, J., Dong, X., Liu, L., Zhang, C., Shen, J., & Yu, D. (2022) · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52688.2022.01367 · Cited by 137
“On the other hand, self-attention designed for video tasks suggests that the transformer-based method can establish the interaction between spatial and temporal domain [1, 3, 15, 40].”
BackgroundMethodInfluentialWu, W., Wang, X., Luo, H., Wang, J., Yang, Y., & Ouyang, W. (2023) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52729.2023.00640 · Cited by 136
“Additionally, researchers have started to adopt transformers for video recognition, such as TimeSFormer [2], ViViT [1], VideoSwin [30], and MViT [11].”
MethodAvatarPoser: Articulated Full-Body Pose Tracking from Sparse Motion Sensing
Jiang, J., Streli, P., Qiu, H., Fender, A. R., Laich, L., Snape, P., & Holz, C. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-20065-6_26 · Cited by 128
ReconFormer: Accelerated MRI Reconstruction Using Recurrent Transformer
Guo, P., Mei, Y., Zhou, J., Jiang, S., & Patel, V. M. (2023) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2023.3314747 · Cited by 129
“To overcome this weakness, most recent Transformers (PVT [26], Swin Transformer [25], MViT [55], ViL [56]) for high-level vision adapt hierarchical structures, which can be view as a stack of multiple ViTs with reduced resolution.”
BackgroundBidirectional Multi-Scale Implicit Neural Representations for Image Deraining
Chen, X., Pan, J., & Dong, J. (2024) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52733.2024.02421 · Cited by 128
“The detailed descriptions of the used training and testing datasets are tabulated in Table 1.”
MethodSVFormer: Semi-supervised Video Transformer for Action Recognition
Xing, Z., Dai, Q., Han, H., Chen, J., Wu, Z., & Jiang, Y. (2023) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52729.2023.01804 · Cited by 130
“In addition, MviT [14], Video Swin [31] and Uniformer [28] incorporate the inductive bias in convolution into transformers.”
BackgroundThree Things Everyone Should Know About Vision Transformers
Touvron, H., Cord, M., El-Nouby, A., Verbeek, J. J., & Jeǵou, H. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-20053-3_29 · Cited by 150
CycleMLP: A MLP-Like Architecture for Dense Visual Predictions
Chen, S., Xie, E., Ge, C., Chen, R., Liang, D., & Luo, P. (2023) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2023.3303397 · Cited by 311
“…transformers have also dominated computer vision since the invention of ViT [23], and have been considered as a de facto standard for various tasks, such as image classification [23], [91], [118], detection and segmentation [60], [99], [108], [126], video recognition [1], [3], [25], [100] and so on.”
BackgroundMethodVita-CLIP: Video and text adaptive CLIP via Multimodal Prompting
Wasim, S. T., Naseer, M., Khan, S., Khan, F. S., & Shah, M. A. (2023) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52729.2023.02206 · Cited by 140
Towards multimodal foundation models in molecular cell biology
Cui, H., Tejada-Lapuerta, A., Brbić, M., Sáez-Rodríguez, J., Cristea, S., Goodarzi, H., Lotfollahi, M., Theis, F. J., & Wang, B. (2025) · Nature · doi:10.1038/s41586-025-08710-y · Cited by 151
“Although multilevel attention has been applied in milestone studies in computer vision, such as SwinTransformer 91 and MultiScale ViT 92 , similar ideas in biological foundation models are yet to be explored.”
Multi-Modal Feature Pyramid Transformer for RGB-Infrared Object Detection
Zhu, Y.-H., Sun, X., Wang, M., & Huang, H. (2023) · IEEE transactions on intelligent transportation systems (Print) · doi:10.1109/tits.2023.3266487 · Cited by 130
“[39] create a multi-head pooling attention operation to obtain coarse-grained tokens, which are used to conduct self-attention to capture long-range relationships.”
BackgroundTallFormer: Temporal Action Localization with a Long-Memory Transformer
Cheng, F., & Bertasius, G. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-19830-4_29 · Cited by 123
Selective Structured State-Spaces for Long-Form Video Understanding
Wang, J., Zhu, W., Wang, P., Yu, X., Liu, L. L., Omar, M., & Hamid, R. (2023) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52729.2023.00618 · Cited by 131
“The recent vision transformer (ViT) [14] has shown promising capability in modeling long-range dependencies, and several variants [1,4,15,44,49,54,70] have successfully adopted the transformer architecture for video modeling.”
BackgroundSelf-supervised Video Transformer
Ranasinghe, K., Naseer, M., Khan, S. H., Khan, F. S., & Ryoo, M. S. (2022) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52688.2022.00289 · Cited by 128
“ViTs have also been adopted for video classification tasks [4, 9, 29, 67, 68].”
BackgroundMethodVideo Understanding With Large Language Models: A Survey
Tang, Y., Bi, J., Xu, S., Song, L., Liang, S., Wang, T., Zhang, D., An, J., Lin, J., Zhu, R., et al. (2025) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2025.3566695 · Cited by 288
“The introduction of Vision Transformers (ViT) [45] promotes a series of prominent models (e.g., TimeSformer [46], VidTr [47], ViViT [48], MViT [49]).”
MethodYu, Q., Wang, H., Qiao, S., Collins, M. D., Zhu, Y., Adam, H., Yuille, A., & Chen, L.-C. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-19818-2_17 · Cited by 123
Slide-Transformer: Hierarchical Vision Transformer with Local Self-Attention
Pan, X., Ye, T., Xia, Z., Song, S., & Huang, G. M. (2023) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52729.2023.00207 · Cited by 119
“MViT [11, 18] considers the pooling function on the input to obtain key and value pairs, which can be seen as a lower resolution of the feature map.”
BackgroundActionCLIP: Adapting Language-Image Pretrained Models for Video Action Recognition
Wang, M., Xing, J., Mei, J., Liu, Y., & Jiang, Y. (2023) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2023.3331841 · Cited by 592
Unsupervised video anomaly detection via normalizing flows with implicit latent features
Cho, M., Kim, T., Kim, W. J., Cho, S., & Lee, S. (2022) · Pattern Recognition · doi:10.1016/j.patcog.2022.108703 · Cited by 111
“…[2] divide space and time information to perform self-attention using a sequence of spatio-temporal tokens; Multiscale Vision Transform-ers (MViT) [11] contains several channel-resolution scale stages to create a multiscale pyramid of feature activation; Swin-T [30] extends the Swin Transformer…”
BackgroundMARLIN: Masked Autoencoder for facial video Representation LearnINg
Cai, Z., Ghosh, S., Stefanov, K., Dhall, A., Cai, J., Rezatofighi, H., Haffari, R., & Hayat, M. (2023) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52729.2023.00150 · Cited by 122
“MViT-v1 [30] and MViT-v2 [49]) and CNNs (i.”
Revisiting Classifier: Transferring Vision-Language Models for Video Recognition
Wu, W., Sun, Z., & Ouyang, W. (2023) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v37i3.25386 · Cited by 120
“Also, many works has begun to adopt transformers in video recognition, such as TimeSFormer [2], ViViT [1], VideoSwin [36], and MViT [11].”
BackgroundTubeR: Tubelet Transformer for Video Action Detection
Zhao, J., Zhang, Y., Li, X., Chen, H., Shuai, B., Xu, M., Liu, C., Kundu, K., Xiong, Y., Modolo, D., et al. (2022) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52688.2022.01323 · Cited by 101
“Recent works show that transformer encoders can be used for video embedding [2, 7, 46] and are less memory and computationally hungry.”
BackgroundInfluentialRevisiting Weakly Supervised Pre-Training of Visual Perception Models
Singh, M., Gustafson, L., Adcock, A., De Freitas Reis, V., Gedik, B., Kosaraju, R. P., Mahajan, D., Girshick, R., Dollar, P., & Van Der Maaten, L. (2022) · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52688.2022.00088 · Cited by 99
“Fully supervised pre-training was pioneered by [19, 59] and is now the de-facto standard approach to a variety of visual-recognition tasks, including fine-grained image classification [30, 62], object detection [61], image segmentation [32, 70], image captioning [46], visual question answering [40], video classificati…”
BackgroundROAD: The Road Event Awareness Dataset for Autonomous Driving
Singh, G., Akrigg, S., Maio, M. D., Fontana, V., Alitappeh, R. J., Khan, S., Saha, S., Jeddisaravi, K., Yousefi, F., Culley, J., et al. (2022) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2022.3150906 · Cited by 99
“stronger backbones using transformers [106], [107] can be plugged in.”
BackgroundSTIP-GCN: Space-time interest points graph convolutional network for action recognition
Yenduri, S., Chalavadi, V., & Mohan, C. K. (2022) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn55064.2022.9891959 · Cited by 98
“Inspired by the success of transformers in NLP tasks, some of the methods [43], [44], [47] incorporated variants of transformers to attend to spatial and temporal information.”
MethodDeep Frequency Filtering for Domain Generalization
Lin, S., Zhang, Z., Huang, Z., Lü, Y., Lan, C., Chu, P., You, Q., Wang, J., Liu, Z., Parulkar, A., et al. (2023) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52729.2023.01135 · Cited by 105
“It can be roughly categorized into selective attention [44, 45, 46, 47, 48, 49, 50] and self-attention [51, 46, 52, 53, 54, 55, 56, 57] according to their working mechanisms.”
Long Movie Clip Classification with State-Space Video Models
Islam, M. M., & Bertasius, G. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-19833-5_6 · Cited by 107
Yang, M., Chengke, W., Guo, Y., Jiang, R., Zhou, F., Zhang, J., & Yang, Z. (2022) · Automation in Construction · doi:10.1016/j.autcon.2022.104703 · Cited by 103
ShadowFormer: Global Context Helps Shadow Removal
Guo, L., Huang, S., Liu, D., Cheng, H., & Wen, B. (2023) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v37i1.25148 · Cited by 143
DropKey for Vision Transformer
Li, B., Hu, Y., Nie, X., Han, C., Jiang, X., Guo, T., & Liu, L. (2023) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52729.2023.02174 · Cited by 106
“Vision Transformer (ViT) [6] has achieved great success for various vision tasks, e.g. , image recognition [7, 12, 20, 34, 35], object detection [1], human body shape estimation [18], etc. Prior works mainly focus on researches of patch division, architecture design and task extension.”
BackgroundNeighbourhood Representative Sampling for Efficient End-to-End Video Quality Assessment
Wu, H., Chen, C., Liao, L., Hou, J., Sun, W., Yan, Q., Gu, J., & Lin, W. (2023) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2023.3319332 · Cited by 112
“Many backbone structures can meet this requirement, including transformer-based structures [24], [26], [27], [50] and part of modern convolution-based structures such as ConvNeXt [51], while it is possible to match their pooling kernels with mini-cubes.”
BackgroundSnyder, Q., Jiang, Q., & Tripp, E. E. (2024) · Signal Processing · doi:10.1016/j.sigpro.2024.109683 · Cited by 95
Dual-AI: Dual-path Actor Interaction Learning for Group Activity Recognition
Han, M., Zhang, D. J., Wang, Y., Yan, R., Yao, L., Chang, X., & Qiao, Y. (2022) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52688.2022.00300 · Cited by 91
“In video domain, many works [5,8,17,19,29,35] explore spatial and temporal self-attention to learn efficient video representation.”
BackgroundMethod
Metadata
- Authors
- Fan, H., Xiong, B., Mangalam, K., Li, Y., Yan, Z., Malik, J., & Feichtenhofer, C.
- Affiliations
- Meta (Israel) (IL)
- Meta (United States) (US)
- Venue
- 2021 IEEE/CVF International Conference on Computer Vision (ICCV)
- Publisher
- IEEE
- Published
- 2021-10
- Pages
- 6804-6815
- OpenAlex
- W3202698164
- Cited by
- 1,407
- References
- 111
- Citations by year
- 2026: 147 · 2025: 345 · 2024: 380 · 2023: 349 · 2022: 176 · 2021: 10
- FWCI
- 74.81
- Type
- conference paper
- Language
- en
- Open access
- green
- arxiv.org
- Locations
- IEEE/CVF International Conference on Computer Vision (ICCV) (publishedVersion)
- arXiv (Cornell University)
- TIB Data Manager
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Human Pose and Action Recognition
- Physical Sciences › Computer Science › Artificial Intelligence › Domain Adaptation and Few-Shot Learning
- Keywords
- video recognition, image classification, feature pyramid, spatial resolution reduction, computational efficiency
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
