74 citations · 152 across the 17 of their papers we have counts for
17 papers
ACE-Ego-Hand: Repurposing Video Diffusion Models for Occlusion-Robust Egocentric 3D Hand Motion Recovery
Yufei Liu, Xixi Wang, Hao Li +8
Egocentric video offers scalable manipulation data for embodied AI, yet recovering metric 3D hand trajectories remains challenging due to severe object occlusion and frequent out-o…
ACE-Ego-0: Unifying Egocentric Human and Robotic Data for VLA Pretraining
Hao Li, Ganlong Zhao, Yufei Liu +8
Vision-Language-Action (VLA) models benefit from large-scale and diverse embodied data, yet scaling robot trajectory collection is costly and labor-intensive. Recent advances show…
Hierarchical Advantage Weighting for Online RL Fine-Tuning of VLAs from Sparse Episode Outcomes
Tongyan Fang, Siyuan Huang, Naiyu Fang +6
When pretrained VLA policies are fine-tuned through online RL, each rollout episode produces only a single binary outcome (success or failure), yet the actor update requires per-tr…
Rethinking VLM Representation for VLA Initialization
Weifeng Lin, Siyuan Huang, Hao Li +5
Vision-Language-Action (VLA) models widely adopt pretrained Vision-Language Models (VLMs) as policy backbones, yet it remains unclear what kind of pretrained VLM representation is…
Mutual Exclusive Modulator for Long-Tailed Recognition
Haixu Long, Xiaolin Zhang, Yanbin Liu +2
The long-tailed recognition (LTR) is the task of learning high-performance classifiers given extremely imbalanced training samples between categories. Most of the existing works ad…
Deep Dynamic Scene Deblurring from Optical Flow
Jiawei Zhang, Jinshan Pan, Daoye Wang +5
Deblurring can not only provide visually more pleasant pictures and make photography more convenient, but also can improve the performance of objection detection as well as trackin…
Fraud Dataset Benchmark and Applications
Prince Grover, Julia Xu, Justin Tittelfitz +5
Standardized datasets and benchmarks have spurred innovations in computer vision, natural language processing, multi-modal and tabular settings. We note that, as compared to other…
Pyramid Fusion Transformer for Semantic Segmentation
Zipeng Qin, Jianbo Liu, Xiaolin Zhang +4
The recently proposed MaskFormer gives a refreshed perspective on the task of semantic segmentation: it shifts from the popular pixel-level classification paradigm to a mask-level…
Encoder-decoder with Multi-level Attention for 3D Human Shape and Pose Estimation
Ziniu Wan, Zhengjia Li, Maoqing Tian +3
3D human shape and pose estimation is the essential task for human motion analysis, which is widely used in many 3D applications. However, existing methods cannot simultaneously ca…
Learning N:M Fine-grained Structured Sparse Neural Networks From Scratch
Aojun Zhou, Yukun Ma, Junnan Zhu +5
Sparsity in Deep Neural Networks (DNNs) has been widely studied to compress and accelerate the models on resource-constrained environments. It can be generally categorized into uns…
A Holistically-Guided Decoder for Deep Representation Learning with Applications to Semantic Segmentation and Object Detection
Jianbo Liu, Sijie Ren, Yuanjie Zheng +2
Both high-level and high-resolution feature representations are of great importance in various visual understanding tasks. To acquire high-resolution feature maps with high-level s…
EfficientFCN: Holistically-guided Decoding for Semantic Segmentation
Jianbo Liu, Junjun He, Jiawei Zhang +2
Both performance and efficiency are important to semantic segmentation. State-of-the-art semantic segmentation algorithms are mostly based on dilated Fully Convolutional Networks (…
Learning to Predict Context-adaptive Convolution for Semantic Segmentation
Jianbo Liu, Junjun He, Jimmy S. Ren +2
Long-range contextual information is essential for achieving high-performance semantic segmentation. Previous feature re-weighting methods demonstrate that using global context for…
Learning Selfie-Friendly Abstraction from Artistic Style Images
Yicun Liu, Jimmy Ren, Jianbo Liu +2
Artistic style transfer can be thought as a process to generate different versions of abstraction of the original image. However, most of the artistic style transfer operators are…
LSTM Pose Machines
Yue Luo, Jimmy Ren, Zhouxia Wang +5
We observed that recent state-of-the-art results on single image human pose estimation were achieved by multi-stage Convolution Neural Networks (CNN). Notwithstanding the superior…
Robust Tracking Using Region Proposal Networks
Jimmy Ren, Zhiyang Yu, Jianbo Liu +5
Recent advances in visual tracking showed that deep Convolutional Neural Networks (CNN) trained for image classification can be strong feature extractors for discriminative tracker…
Accurate Single Stage Detector Using Recurrent Rolling Convolution
Jimmy Ren, Xiaohao Chen, Jianbo Liu +5
Most of the recent successful methods in accurate object detection and localization used some variants of R-CNN style two stage Convolutional Neural Networks (CNN) where plausible…