Ting Zhang

Ting Zhang

Auto-generated profile, based on publicly available information

Ting Zhang

Microsoft Research Asia

Research Focus & Metrics

Academic Career Length

9Years (2018-Present)

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

Representative Publications

View All Publications
17 October 2023 in IEEE Transactions on Visualization and Computer Graphics
Verified
Journal Article
Closed access
JTJunshu Tang
Junshu Tang
BZBo Zhang
Bo Zhang
BYBinxin Yang
Binxin Yang
TZTing Zhang
Ting Zhang
DCDong Chen
Dong Chen
FWFang Wen
Fang Wen
In contrast to the traditional avatar creation pipeline which is a costly process, contemporary generative approaches directly learn the data distribution from photographs. While plenty of works extend unconditional generative models and achieve some levels of controllability, it is still challenging to ensure multi-view consistency, especially in large poses. In this work, we propose a network that generates 3D-aware portraits while being controllable according to semantic parameters regarding pose, identity, expression and illumination. Our network uses neural scene representation to model 3D-aware portraits, whose generation is guided by a parametric face model that supports explicit control. While the latent disentanglement can be further enhanced by contrasting images with partially different attributes, there still exists noticeable inconsistency in non-face areas when animating expressions. We solve this by proposing a volume blending strategy in which we form a composite output by blending dynamic and static areas, with two parts segmented from the jointly learned semantic field. Our method outperforms prior arts in extensive experiments, producing realistic portraits with vivid expression in natural lighting when viewed from free viewpoints. It also demonstrates generalization ability to real images as well as out-of-domain data, showing great promise in real applications.

5 December 2024
Verified
Book Chapter
Closed access
PDF file
BZBowen Zhang
Bowen Zhang
YCYiji Cheng
Yiji Cheng
CWChunyu Wang
Chunyu Wang
TZTing Zhang
Ting Zhang
JYJiaolong Yang
Jiaolong Yang
BGBaining Guo
Baining Guo

11 May 2018 in IEEE Transactions on Pattern Analysis and Machine Intelligence
Verified
Journal Article
Closed access
JWJingdong Wang
Jingdong Wang
TZTing Zhang
Ting Zhang
This paper studies the compact coding approach to approximate nearest neighbor search. We introduce a composite quantization framework. It uses the composition of several ($M$) elements, each of which is selected from a different dictionary, to accurately approximate a $D$-dimensional vector, thus yielding accurate search, and represents the data vector by a short code composed of the indices of the selected elements in the corresponding dictionaries. Our key contribution lies in introducing a near-orthogonality constraint, which makes the search efficiency is guaranteed as the cost of the distance computation is reduced to $O(M)$ from $O(D)$ through a distance table lookup scheme. The resulting approach is called near-orthogonal composite quantization. We theoretically justify the equivalence between near-orthogonal composite quantization and minimizing an upper bound of a function formed by jointly considering the quantization error and the search cost according to a generalized triangle inequality. We empirically show the efficacy of the proposed approach over several benchmark datasets. In addition, we demonstrate the superior performances in other three applications: combination with inverted multi-index, inner-product similarity search, and query compression for mobile search.

28 July 2020 in IEEE Transactions on Pattern Analysis and Machine Intelligence
Verified
Journal Article
Closed access
XMXiang Ming
Xiang Ming
FWFangyun Wei
Fangyun Wei
TZTing Zhang
Ting Zhang
DCDong Chen
Dong Chen
NZNanning Zheng
Nanning Zheng
FWFang Wen
Fang Wen
Detectors based on deep learning tend to detect multi-scale faces on a single input image for efficiency. Recent works, such as FPN and SSD, generally use feature maps from multiple layers with different spatial resolutions to detect objects at different scales, e.g., high-resolution feature maps for small objects. However, we find that objects at all scales can also be well detected with features from a single layer of the network. In this paper, we carefully examine the factors affecting detection performance across a large range of scales, and conclude that the balance of training samples, including both positive and negative ones, at different scales is the key. We propose a group sampling method which divides the anchors into several groups according to the scale, and ensure that the number of samples for each group is the same during training. Our approach using only one single layer of FPN is able to advance the state-of-the-arts. Comprehensive analysis and extensive experiments have been conducted to show the effectiveness of the proposed method. Moreover, we show that our approach is favorably applicable to other detection tasks and to other pipelines. Our approach achieves state-of-the-art results on several face detection benchmarks without bells and whistles.

9 November 2026
Verified
Conference Paper
Open access
YWYuqi Wang
Yuqi Wang
QBQian Bao
Qian Bao
YAYingying Ao
Yingying Ao
TZTing Zhang
Ting Zhang
HYHaotian Yang
Haotian Yang
JFJintao Fang
Jintao Fang

26 May 2026 in Graphical Models
Verified
Journal Article
Open access
TZTing Zhang
Ting Zhang
JWJunxiao Wang
Junxiao Wang
HYHeng Yu
Heng Yu
QXQunyi Xie
Qunyi Xie
JWJingdong Wang
Jingdong Wang
HHHua Huang
Hua Huang