publications
publications by categories in reversed chronological order. generated by jekyll-scholar.
2026
- MV-S2V: Multi-View Subject-Consistent Video GenerationarXiv preprint arXiv:2601.17756, 2026
2025
- ByteLoom: Weaving Geometry-Consistent Human-Object Interactions through Progressive Curriculum LearningarXiv preprint arXiv:2512.22854, 2025
- CETCAM: Camera-Controllable Video Generation via Consistent and Extensible TokenizationarXiv preprint arXiv:2512.19020, 2025
2024
- Grounded-instruct-pix2pix: Improving instruction based image editing with automatic target groundingIn ICASSP 2024-2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2024
2023
- MMG-Ego4D: Multi-Modal Generalization in Egocentric Action RecognitionIn The IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2023, 2023
- WS-iFSD: Weakly Supervised Incremental Few-shot Object Detection Without ForgettingIn Conference on Parsimony and Learning (Proceedings Track), 2023
2022
- Auto-X3D: Ultra-efficient video understanding via finer-grained neural architecture searchIn Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, 2022
- Sandwich batch normalization: A drop-in replacement for feature distribution heterogeneityIn Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, 2022
- Deep Architecture Connectivity Matters for Its Convergence: A Fine-Grained AnalysisIn NeurIPS 2022, 2022
- Unified Implicit Neural StylizationIn ECCV 2022, 2022
- NeRF-SOS: Any-View Self-supervised Object Segmentation on Complex ScenesIn ICLR 2023, 2022
2021
- Neural architecture search on imagenet in four gpu hours: A theoretically inspired perspectiveIn ICLR 2021, 2021
- Understanding and Accelerating Neural Architecture Search with Training-Free and Theory-Grounded MetricsTPAMI, 2021
- Searching for Two-Stream Models in Multivariate Space for Video RecognitionIn International Conference on Computer Vision (ICCV) 2021, 2021
- SAFIN: arbitrary style transfer with self-attentive factorized instance normalizationarXiv preprint arXiv:2105.06129, 2021
2020
- AutoSpeech: Neural Architecture Search for Speaker RecognitionInterSpeech 2020, 2020
- NADS: Neural Architecture Distribution Search for Uncertainty AwarenessIn International Conference on Machine Learning (ICML) 2020, 2020
- Autopose: Searching multi-scale branch aggregation for pose estimationarXiv preprint arXiv:2008.07018, 2020
2019
- Conditional adversarial generative flow for controllable image synthesisIn Computer Vision and Pattern Recognition (CVPR), 2019
- Enlightengan: Deep light enhancement without paired supervisionTIP, 2019
- AutoGAN: Neural Architecture Search for Generative Adversarial NetworksIn IEEE International Conference on Computer Vision (ICCV) 2019, 2019
- FasterSeg: Searching for Faster Real-time Semantic SegmentationIn International Conference on Learning Representations (ICLR) 2020, 2019
- EnlightenGAN: Deep light enhancement without paired supervision. arXiv 2019arXiv preprint arXiv:1906.06972, 2019
2018
- Neural Stereoscopic Image Style TransferIn The European Conference on Computer Vision (ECCV), 2018, pp. 54-69, 2018
- Multitarget AOA estimation using wideband LFMCW signal and two receiver antennasIEEE Transactions on Vehicular Technology (TVT), 2018