no code implementations • 25 Mar 2024 • Zicong Fan, Takehiko Ohkawa, Linlin Yang, Nie Lin, Zhishan Zhou, Shihao Zhou, Jiajun Liang, Zhong Gao, Xuanyang Zhang, Xue Zhang, Fei Li, Liu Zheng, Feng Lu, Karim Abou Zeid, Bastian Leibe, Jeongwan On, Seungryul Baek, Aditya Prakash, Saurabh Gupta, Kun He, Yoichi Sato, Otmar Hilliges, Hyung Jin Chang, Angela Yao
We interact with the world with our hands and see it through our own (egocentric) perspective.
no code implementations • 4 Mar 2024 • Zhishan Zhou, Shihao. zhou, Zhi Lv, Minqiang Zou, Yao Tang, Jiajun Liang
3D hand pose estimation has found broad application in areas such as gesture recognition and human-machine interaction tasks.
Ranked #2 on 3D Hand Pose Estimation on DexYCB
no code implementations • 6 Dec 2023 • Linze Li, Sunqi Fan, Hengjun Pu, Zhaodong Bing, Yao Tang, Tianzhu Ye, Tong Yang, Liangyu Chen, Jiajun Liang
Our method's efficacy has been validated on multiple representative DreamBooth and LoRA models, delivering substantial improvements over the original outcomes in terms of facial fidelity, text-to-image editability, and video motion.
no code implementations • 1 Dec 2023 • Huadong Li, Minhao Jing, Jiajun Liang, Haoqiang Fan, Renhe Ji
In this paper, we find that the challenge of using sparse supervision for training Radar-Camera depth prediction models is the Projection Transformation Collapse (PTC).
no code implementations • 29 Nov 2023 • Shen Zhang, Zhaowei Chen, Zhenyu Zhao, Zhenyuan Chen, Yao Tang, Yuhao Chen, Wengang Cao, Jiajun Liang
We introduce HiDiffusion, a tuning-free framework comprised of Resolution-Aware U-Net (RAU-Net) and Modified Shifted Window Multi-head Self-Attention (MSW-MSA) to enable pretrained large text-to-image diffusion models to efficiently generate high-resolution images (e. g. 1024$\times$1024) that surpass the training image resolution.
no code implementations • 20 Oct 2023 • Kexin Zhu, Bo Lin, Yang Qiu, Adam Yule, Yao Tang, Jiajun Liang
We introduce a high-performance fingerprint liveness feature extraction technique that secured first place in LivDet 2023 Fingerprint Representation Challenge.
no code implementations • 7 Oct 2023 • Zhishan Zhou, Zhi Lv, Shihao Zhou, Minqiang Zou, Tong Wu, Mochen Yu, Yao Tang, Jiajun Liang
This report introduce our work on Egocentric 3D Hand Pose Estimation workshop.
no code implementations • ICCV 2023 • Borui Zhao, RenJie Song, Jiajun Liang
(2) Distilling knowledge from CNN limits the network convergence in the later training period since ViT's capability of integrating global information is suppressed by CNN's local-inductive-bias supervision.
no code implementations • ICCV 2023 • Borui Zhao, Quan Cui, RenJie Song, Jiajun Liang
In this paper, we observe a trade-off between task and distillation losses, i. e., introducing distillation loss limits the convergence of task loss.
1 code implementation • CVPR 2023 • Siyuan Wei, Tianzhu Ye, Shen Zhang, Yao Tang, Jiajun Liang
Experiments on various transformers demonstrate the effectiveness of our method, while analysis experiments prove our higher robustness to the errors of the token pruning policy.
Ranked #1 on Efficient ViTs on ImageNet-1K (with DeiT-S)
1 code implementation • CVPR 2023 • Yuhao Chen, Xin Tan, Borui Zhao, Zhaowei Chen, RenJie Song, Jiajun Liang, Xuequan Lu
ANL introduces the additional negative pseudo-label for all unlabeled data to leverage low-confidence examples.
1 code implementation • 13 Mar 2023 • Shuangping Jin, Bingbing Yu, Minhao Jing, Yi Zhou, Jiajun Liang, Renhe Ji
To handle this, we propose a new RGB-NIR fusion algorithm called Dark Vision Net (DVN) with two technical novelties: Deep Structure and Deep Inconsistency Prior (DIP).
1 code implementation • CVPR 2023 • Shichao Dong, Jin Wang, Renhe Ji, Jiajun Liang, Haoqiang Fan, Zheng Ge
In this paper, we analyse the generalization ability of binary classifiers for the task of deepfake detection.
1 code implementation • 26 Oct 2022 • Zhi Lv, Bo Lin, Siyuan Liang, Lihua Wang, Mochen Yu, Yao Tang, Jiajun Liang
We present a simple domain generalization baseline, which wins second place in both the common context generalization track and the hybrid context generalization track respectively in NICO CHALLENGE 2022.
1 code implementation • 26 Jul 2022 • Jiajun Liang, Linze Li, Zhaodong Bing, Borui Zhao, Yao Tang, Bo Lin, Haoqiang Fan
This paper proposes an efficient self-distillation method named Zipf's Label Smoothing (Zipf's LS), which uses the on-the-fly prediction of a network to generate soft supervision that conforms to Zipf distribution without using any contrastive samples or auxiliary parameters.
1 code implementation • 20 Jul 2022 • Shichao Dong, Jin Wang, Jiajun Liang, Haoqiang Fan, Renhe Ji
Besides the supervision of binary labels, deepfake detection models implicitly learn artifact-relevant visual concepts through the FST-Matching (i. e. the matching fake, source, target images) in the training set.
1 code implementation • CVPR 2022 • Borui Zhao, Quan Cui, RenJie Song, Yiyu Qiu, Jiajun Liang
To provide a novel viewpoint to study logit distillation, we reformulate the classical KD loss into two parts, i. e., target class knowledge distillation (TCKD) and non-target class knowledge distillation (NCKD).
1 code implementation • 8 Mar 2022 • Quan Cui, Bingchen Zhao, Zhao-Min Chen, Borui Zhao, RenJie Song, Jiajun Liang, Boyan Zhou, Osamu Yoshie
This work simultaneously considers the discriminability and transferability properties of deep representations in the typical supervised learning task, i. e., image classification.
1 code implementation • CVPR 2022 • Lingfeng Yang, Xiang Li, RenJie Song, Borui Zhao, Juntian Tao, Shihao Zhou, Jiajun Liang, Jian Yang
Therefore, it is helpful to leverage additional information, e. g., the locations and dates for data shooting, which can be easily accessible but rarely exploited.
no code implementations • NeurIPS 2021 • Jiashun Jin, Tracy Ke, Jiajun Liang
In a broad Degree-Corrected Mixed-Membership (DCMM) setting, we test whether a non-uniform hypergraph has only one community or has multiple communities.
no code implementations • 29 Jan 2021 • Jiajun Liang, Chuyang Ke, Jean Honorio
Our bounds are tight and pertain to the community detection problems in various models such as the planted hypergraph stochastic block model, the planted densest sub-hypergraph model, and the planted multipartite hypergraph model.
no code implementations • 18 Sep 2018 • Minghui Liao, Jian Zhang, Zhaoyi Wan, Fengming Xie, Jiajun Liang, Pengyuan Lyu, Cong Yao, Xiang Bai
Inspired by speech recognition, recent state-of-the-art algorithms mostly consider scene text recognition as a sequence prediction problem.
Ranked #30 on Scene Text Recognition on SVT
32 code implementations • CVPR 2017 • Xinyu Zhou, Cong Yao, He Wen, Yuzhi Wang, Shuchang Zhou, Weiran He, Jiajun Liang
Previous approaches for scene text detection have already achieved promising performances across various benchmarks.
Ranked #3 on Scene Text Detection on COCO-Text
Curved Text Detection Optical Character Recognition (OCR) +1