LC
Liang-Chieh Chen
cs.CVcs.LGcs.AIeess.IVstat.MLcs.NE
On Valency
published · living versionsW_87gzj669·v1 · currentpublished
DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs
with George Papandreou, Iasonas Kokkinos, Kevin Murphy, Alan L. Yuille
1 version
Preprints & journals
73 papers in the corpus · 2014–2026Taming Outlier Tokens in Diffusion Transformers2605.05206v1 · Xiaoyu Wu, Yifei Wang, Tsu-Jui Fu et al.2026 · 0 citationsarXiv
Large Language Models are Universal Reasoners for Visual Generation2605.04040v1 · Sucheng Ren, Chen Chen, Zhenbang Wang et al.2026 · 0 citationsarXiv
Frequency-Aware Flow Matching for High-Quality Image Generation2604.15521v1 · Sucheng Ren, Qihang Yu, Ju He et al.2026 · 0 citationsarXiv
A Frame is Worth One Token: Efficient Generative World Modeling with Delta Tokens2604.04913v1 · Tommie Kerssies, Gabriele Berton, Ju He et al.2026 · 0 citationsarXiv
Autoregressive Image Generation with Masked Bit Modeling2602.09024v1 · Qihang Yu, Qihao Liu, Ju He et al.2026 · 0 citationsarXiv
ReVision: Refining Video Diffusion with Explicit 3D Motion Modeling2504.21855v2 · Qihao Liu, Ju He, Qihang Yu et al.2025 · 0 citationsarXiv
FlowTok: Flowing Seamlessly Across Text and Image Tokens2503.10772v3 · Ju He, Qihang Yu, Qihao Liu et al.2025 · 8 citationsarXiv
Deeply Supervised Flow-Based Generative Models2503.14494v2 · Inkyu Shin, Chenglin Yang, Liang-Chieh Chen2025 · 1 citationarXiv
Democratizing Text-to-Image Masked Generative Models with Compact Text-Aware One-Dimensional Tokens2501.07730v2 · Dongwon Kim, Ju He, Qihang Yu et al.2025 · 8 citationsarXiv
Grouping First, Attending Smartly: Training-Free Acceleration for Diffusion Transformers2505.14687v1 · Sucheng Ren, Qihang Yu, Ju He et al.2025 · 0 citationsarXiv
Enhancing Temporal Consistency in Video Editing by Reconstructing Videos with 3D Gaussian Splatting2406.02541v4 · Inkyu Shin, Qihang Yu, Xiaohui Shen et al.2024 · 0 citationsarXiv
ViCaS: A Dataset for Combining Holistic and Pixel-level Video Understanding using Captions with Grounded Segmentation2412.09754v3 · Ali Athar, Xueqing Deng, Liang-Chieh Chen2024 · 4 citationsarXiv
Beyond Next-Token: Next-X Prediction for Autoregressive Visual Generation2502.20388v2 · Sucheng Ren, Qihang Yu, Ju He et al.2025 · 8 citationsarXiv
COCONut-PanCap: Joint Panoptic Segmentation and Grounded Captions for Fine-Grained Understanding and Generation2502.02589v1 · Xueqing Deng, Qihang Yu, Ali Athar et al.2025 · 0 citationsarXiv
1.58-bit FLUX2412.18653v1 · Chenglin Yang, Celong Liu, Xueqing Deng et al.2024 · 1 citationarXiv
FlowAR: Scale-wise Autoregressive Image Generation Meets Flow Matching2412.15205v1 · Sucheng Ren, Qihang Yu, Ju He et al.2024 · 0 citationsarXiv
MaskBit: Embedding-free Image Generation via Bit Tokens2409.16211v2 · Mark Weber, Lijun Yu, Qihang Yu et al.2024 · 0 citationsarXiv
Alleviating Distortion in Image Generation via Multi-Resolution Diffusion Models and Time-Dependent Layer Normalization2406.09416v2 · Qihao Liu, Zhanpeng Zeng, Ju He et al.2024 · 3 citationsarXiv
Randomized Autoregressive Visual Generation2411.00776v1 · Qihang Yu, Ju He, Xueqing Deng et al.2024 · 9 citationsarXiv
A Simple Video Segmenter by Tracking Objects Along Axial Trajectories2311.18537v2 · Ju He, Qihang Yu, Inkyu Shin et al.2023 · 2 citationsarXiv
An Image is Worth 32 Tokens for Reconstruction and Generation2406.07550v1 · Qihang Yu, Mark Weber, Xueqing Deng et al.2024 · 22 citationsarXiv
COCONut: Modernizing COCO Segmentation2404.08639v1 · Xueqing Deng, Qihang Yu, Peng Wang et al.2024 · 0 citationsarXiv
ViTamin: Designing Scalable Vision Models in the Vision-Language Era2404.02132v2 · Jieneng Chen, Qihang Yu, Xiaohui Shen et al.2024 · 30 citationsarXiv
SPFormer: Enhancing Vision Transformer with Superpixel Representation2401.02931v1 · Jieru Mei, Liang-Chieh Chen, Alan Yuille et al.2024 · 6 citationsarXiv
MaskConver: Revisiting Pure Convolution Model for Panoptic Segmentation2312.06052v1 · Abdullah Rashwan, Jiageng Zhang, Ali Taalimi et al.2023 · 7 citationsarXiv
Convolutions Die Hard: Open-Vocabulary Segmentation with Single Frozen Convolutional CLIP2308.02487v2 · Qihang Yu, Ju He, Xueqing Deng et al.2023 · 49 citationsarXiv
Towards Open-Ended Visual Recognition with Large Language Model2311.08400v1 · Qihang Yu, Xiaohui Shen, Liang-Chieh Chen2023 · 1 citationarXiv
PolyMaX: General Dense Prediction with Mask Transformer2311.05770v1 · Xuan Yang, Liangzhe Yuan, Kimberly Wilber et al.2023 · 20 citationsarXiv
Superpixel Transformers for Efficient Semantic Segmentation2309.16889v2 · Alex Zihao Zhu, Jieru Mei, Siyuan Qiao et al.2023 · 14 citationsarXiv
kMaX-DeepLab: k-means Mask Transformer2207.04044v5 · Qihang Yu, Huiyu Wang, Siyuan Qiao et al.2022 · 0 citationsarXiv
ReMaX: Relaxing for Better Training on Efficient Panoptic Segmentation2306.17319v1 · Shuyang Sun, Weijun Wang, Qihang Yu et al.2023 · 7 citationsarXiv
DaTaSeg: Taming a Universal Multi-Dataset Multi-Task Segmentation Model2306.01736v1 · Xiuye Gu, Yin Cui, Jonathan Huang et al.2023 · 11 citationsarXiv
Video-kMaX: A Simple Unified Approach for Online and Near-Online Video Panoptic Segmentation2304.04694v1 · Inkyu Shin, Dahun Kim, Qihang Yu et al.2023 · 16 citationsarXiv
A Study of Autoregressive Decoders for Multi-Tasking in Computer Vision2303.17376v1 · Lucas Beyer, Bo Wan, Gagan Madan et al.2023 · 3 citationsarXiv
TubeFormer-DeepLab: Video Mask Transformer2205.15361v2 · Dahun Kim, Jun Xie, Huiyu Wang et al.2022 · 32 citationsarXiv
MOAT: Alternating Mobile Convolution and Attention Brings Strong Vision Models2210.01820v2 · Chenglin Yang, Siyuan Qiao, Qihang Yu et al.2022 · 21 citationsarXiv
CMT-DeepLab: Clustering Mask Transformers for Panoptic Segmentation2206.08948v1 · Qihang Yu, Huiyu Wang, Dahun Kim et al.2022 · 80 citationsarXiv
Waymo Open Dataset: Panoramic Video Panoptic Segmentation2206.07704v1 · Jieru Mei, Alex Zihao Zhu, Xinchen Yan et al.2022 · 60 citationsarXiv
STEP: Segmenting and Tracking Every Pixel2102.11859v2 · Mark Weber, Jun Xie, Maxwell Collins et al.2021 · 9 citationsarXiv
View-Invariant, Occlusion-Robust Probabilistic Embedding for Human Pose2010.13321v3 · Ting Liu, Jennifer J. Sun, Long Zhao et al.2020 · 19 citationsarXiv
MaX-DeepLab: End-to-End Panoptic Segmentation with Mask Transformers2012.00759v3 · Huiyu Wang, Yukun Zhu, Hartwig Adam et al.2020 · 533 citationsarXiv
DeepLab2: A TensorFlow Library for Deep Labeling2106.09748v1 · Mark Weber, Huiyu Wang, Siyuan Qiao et al.2021 · 34 citationsarXiv
Scaling Wide Residual Networks for Panoptic Segmentation2011.11675v2 · Liang-Chieh Chen, Huiyu Wang, Siyuan Qiao2020 · 28 citationsarXiv
ViP-DeepLab: Learning Visual Perception with Depth-aware Video Panoptic Segmentation2012.05258v1 · Siyuan Qiao, Yukun Zhu, Hartwig Adam et al.2020 · 150 citationsarXiv
DetectoRS: Detecting Objects with Recursive Feature Pyramid and Switchable Atrous Convolution2006.02334v2 · Siyuan Qiao, Liang-Chieh Chen, Alan Yuille2020 · 1,179 citationsarXiv
View-Invariant Probabilistic Embedding for Human Pose1912.01001v4 · Jennifer J. Sun, Jiaping Zhao, Liang-Chieh Chen et al.2019 · 73 citationsarXiv
Modeling Image Patches with a Generic Dictionary of Mini-Epitomes.26321859 · Papandreou, George, Chen, Liang-Chieh, Yuille, Alan L2020 · 19 citationsProceedings. IEEE Computer Society Conference on Computer Vision and Pattern Recognition. 2014;2014:2059-2066
Learning a Dictionary of Shape Epitomes with Applications to Image Labeling.26321886 · Chen, Liang-Chieh, Papandreou, George, Yuille, Alan L2020 · 15 citationsProceedings. IEEE International Conference on Computer Vision. 2013;2013:337-344
Axial-DeepLab: Stand-Alone Axial-Attention for Panoptic Segmentation2003.07853v2 · Huiyu Wang, Yukun Zhu, Bradley Green et al.2020 · 733 citationsarXiv
Naive-Student: Leveraging Semi-Supervised Learning in Video Sequences for Urban Scene Segmentation2005.10266v4 · Liang-Chieh Chen, Raphael Gontijo Lopes, Bowen Cheng et al.2020 · 166 citationsarXiv
Career total: 120 works. 73 are in this corpus.Showing the 50 most recent.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.