| Dual path networks Y Chen, J Li, H Xiao, X Jin, S Yan, J Feng NIPS, 4467-4475, 2017 | 1145 | 2017 |
| Deepvit: Towards deeper vision transformer D Zhou, B Kang, X Jin, L Yang, X Lian, Z Jiang, Q Hou, J Feng arXiv preprint arXiv:2103.11886, 2021 | 878 | 2021 |
| Conflict-averse gradient descent for multi-task learning B Liu, X Liu, X Jin, P Stone, Q Liu NeurIPS, 2021, 34, 18878-18890, 2021 | 623 | 2021 |
| Deep learning with s-shaped rectified linear activation units X Jin, C Xu, J Feng, Y Wei, J Xiong, S Yan AAAI, 2016, 2016 | 304 | 2016 |
| All tokens matter: Token labeling for training better vision transformers ZH Jiang, Q Hou, L Yuan, D Zhou, Y Shi, X Jin, A Wang, J Feng NeurIPS, 2021, 34, 18590-18602, 2021 | 292 | 2021 |
| Contrastive masked autoencoders are stronger vision learners Z Huang, X Jin, C Lu, Q Hou, MM Cheng, D Fu, X Shen, J Feng IEEE Transactions on Pattern Analysis and Machine Intelligence 46 (4), 2506-2517, 2023 | 279 | 2023 |
| Deep self-taught learning for weakly supervised object localization Z Jie, Y Wei, X Jin, J Feng, W Liu CVPR, 2017, 1377-1385, 2017 | 246 | 2017 |
| Pixellm: Pixel reasoning with large multimodal model Z Ren, Z Huang, Y Wei, Y Zhao, D Fu, J Feng, X Jin Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern …, 2024 | 225 | 2024 |
| Tree-structured reinforcement learning for sequential object localization Z Jie, X Liang, J Feng, X Jin, W Lu, S Yan NIPS, 2016, 127-135, 2016 | 161 | 2016 |
| Human-centric spatio-temporal video grounding with visual transformers Z Tang, Y Liao, S Liu, G Li, X Jin, H Jiang, Q Yu, D Xu IEEE Transactions on Circuits and Systems for Video Technology 32 (12), 8238 …, 2021 | 155 | 2021 |
| Atomnas: Fine-grained end-to-end neural architecture search J Mei, Y Li, X Lian, X Jin, L Yang, A Yuille, J Yang ICLR 2020, 2019 | 155 | 2019 |
| Video scene parsing with predictive feature learning X Jin, X Li, H Xiao, X Shen, Z Lin, J Yang, Y Chen, J Dong, L Liu, Z Jie, ... ICCV, 2017, 5580-5588, 2017 | 151 | 2017 |
| Vista-llama: Reducing hallucination in video language models via equal distance to visual tokens F Ma, X Jin, H Wang, Y Xian, J Feng, Y Yang Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern …, 2024 | 127* | 2024 |
| Flash-VStream: Efficient Real-Time Understanding for Long Video Streams H Zhang, Y Wang, Y Tang, Y Liu, J Feng, X Jin arXiv preprint arXiv:2506.23825, 2025 | 105* | 2025 |
| Refiner: Refining self-attention for vision transformers D Zhou, Y Shi, B Kang, W Yu, Z Jiang, Y Li, X Jin, Q Hou, J Feng arXiv preprint arXiv:2106.03714, 2021 | 97 | 2021 |
| Training skinny deep neural networks with iterative hard thresholding methods X Jin, X Yuan, J Feng, S Yan arXiv preprint arXiv:1607.05423, 2016 | 96 | 2016 |
| Predicting scene parsing and motion dynamics in the future X Jin, H Xiao, X Shen, J Yang, Z Lin, Y Chen, Z Jie, J Feng, S Yan NIPS, 2017, 6915-6924, 2017 | 88 | 2017 |
| HR-NAS: Searching Efficient High-Resolution Neural Architectures with Lightweight Transformers M Ding, X Lian, L Yang, P Wang, X Jin, Z Lu, P Luo CVPR, 2021, 2982-2992, 2021 | 87 | 2021 |
| Neural Architecture Search for Lightweight Non-Local Networks Y Li, X Jin, J Mei, X Lian, L Yang, C Xie, Q Yu, Y Zhou, S Bai, AL Yuille CVPR, 10297-10306, 2020 | 76 | 2020 |
| Token labeling: Training a 85.5% top-1 accuracy vision transformer with 56m parameters on imagenet Z Jiang, Q Hou, L Yuan, D Zhou, X Jin, A Wang, J Feng arXiv preprint arXiv:2104.10858 3 (6), 7, 2021 | 62 | 2021 |
Jiashi FengByteDance Inc.Adresse e-mail validée de bytedance.com
