Chao Ma

Chao Ma

Auto-generated profile, based on publicly available information

Chao Ma

Shanghai Jiao Tong University

Research Focus & Metrics

Academic Career Length

10Years (2017-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
23 October 2022
Verified
Book Chapter
Closed access
PDF file
SGShenyuan Gao
Shenyuan Gao
CZChunluan Zhou
Chunluan Zhou
CMChao Ma
Chao Ma
Xinggang WangXinggang Wang
Xinggang Wang
JYJunsong Yuan
Junsong Yuan

3 November 2022
Verified
Book Chapter
Closed access
PDF file
GSGuangsheng Shi
Guangsheng Shi
RLRuifeng Li
Ruifeng Li
CMChao Ma
Chao Ma

3 April 2023 in IEEE Transactions on Image Processing
Verified
Journal Article
Closed access
ZWZongwei Wu
Zongwei Wu
GAGuillaume Allibert
Guillaume Allibert
fabrice meriaudeaufabrice meriaudeau
fabrice meriaudeau
CMChao Ma
Chao Ma
CDCédric Demonceaux
Cédric Demonceaux
RGB-D saliency detection aims to fuse multi-modal cues to accurately localize salient regions. Existing works often adopt attention modules for feature modeling, with few methods explicitly leveraging fine-grained details to merge with semantic cues. Thus, despite the auxiliary depth information, it is still challenging for existing models to distinguish objects with similar appearances but at distinct camera distances. In this paper, from a new perspective, we propose a novel Hierarchical Depth Awareness network (HiDAnet) for RGB-D saliency detection. Our motivation comes from the observation that the multi-granularity properties of geometric priors correlate well with the neural network hierarchies. To realize multi-modal and multi-level fusion, we first use a granularity-based attention scheme to strengthen the discriminatory power of RGB and depth features separately. Then we introduce a unified cross dual-attention module for multi-modal and multi-level fusion in a coarse-to-fine manner. The encoded multi-modal features are gradually aggregated into a shared decoder. Further, we exploit a multi-scale loss to take full advantage of the hierarchical information. Extensive experiments on challenging benchmark datasets demonstrate that our HiDAnet performs favorably over the state-of-the-art methods by large margins. The source code can be found in https://github.com/Zongwei97/HIDANet/.

21 September 2020 in International Journal of Computer Vision
Verified
Journal Article
Closed access
PDF file
NWNing Wang
Ning Wang
WZWengang Zhou
Wengang Zhou
YSYibing Song
Yibing Song
CMChao Ma
Chao Ma
WLWei Liu
Wei Liu
HLHouqiang Li
Houqiang Li

16 June 2024
Verified
Conference Paper
Closed access
PTPin Tang
Pin Tang
ZWZhongdao Wang
Zhongdao Wang
GWGuoqing Wang
Guoqing Wang
JZJilai Zheng
Jilai Zheng
XRXiangxuan Ren
Xiangxuan Ren
CMChao Ma
Chao Ma
Vision-based perception for autonomous driving requires an explicit modeling of a 3D space, where 2D latent representations are mapped and subsequent 3D operators are applied. However, operating on dense latent spaces introduces a cubic time and space complexity, which limits scalability in terms of perception range or spatial resolution. Existing approaches compress the dense representation using projections like Bird's Eye View (BEV) or Tri-Perspective View (TPV). Although efficient, these projections result in information loss, especially for tasks like semantic occupancy prediction. To address this, we propose SparseOcc, an efficient occupancy network inspired by sparse point cloud processing. It utilizes a lossless sparse latent representation with three key innovations. Firstly, a 3D sparse diffuser performs latent completion using spatially decomposed 3D sparse convolutional kernels. Secondly, a feature pyramid and sparse interpolation enhance scales with information from others. Finally, the transformer head is redesigned as a sparse variant. SparseOcc achieves a remarkable 74.9% reduction on FLOPs over the dense baseline. Interestingly, it also improves accuracy, from 12.8% to 14.1% mIOU, which in part can be attributed to the sparse representation's ability to avoid hallucinations on empty voxels.

30 November 2020 in IEEE Transactions on Pattern Analysis and Machine Intelligence
Verified
Journal Article
Closed access
Xiankai LuXiankai Lu
Xiankai Lu
CMChao Ma
Chao Ma
JSJianbing Shen
Jianbing Shen
XYXiaokang Yang
Xiaokang Yang
IRIan Reid
Ian Reid
MYMing Yang
Ming Yang
In this paper, we address the issue of data imbalance in learning deep models for visual object tracking. Although it is well known that data distribution plays a crucial role in learning and inference models, considerably less attention has been paid to data imbalance in visual tracking. To balance training data, we propose a novel shrinkage loss to penalize the importance of easy training data mostly coming from the background, which facilitates both deep regression and classification trackers to better distinguish target objects from the background. We extensively validate the proposed shrinkage loss function on six benchmark datasets, including the OTB-2013, OTB-2015, UAV-123, VOT-2016, VOT-2018, and LaSOT. Equipped with our shrinkage loss, the proposed one-stage deep regression tracker achieves favorable results against state-of-the-art methods, especially in comparison with DCFs trackers. Meanwhile, our shrinkage loss generalizes well to deep classification trackers. When replacing the original binary cross-entropy loss with our shrinkage loss, three representative baseline trackers achieve large performance gains, even setting new state-of-the-art results.