Match!
Honggang Zhang
Beijing University of Posts and Telecommunications
73Publications
14H-index
822Citations
Publications 73
Newest
#1Ke Li (Beijing University of Posts and Telecommunications)H-Index: 4
#2Kaiyue Pang (QMUL: Queen Mary University of London)H-Index: 6
Last.Honggang Zhang (Beijing University of Posts and Telecommunications)H-Index: 14
view all 6 authors...
Human free-hand sketches provide the useful data for studying human perceptual grouping, where the grouping principles such as the Gestalt laws of grouping are naturally in play during both the perception and sketching stages. In this paper, we make the first attempt to develop a universal sketch perceptual grouper. That is, a grouper that can be applied to sketches of any category created with any drawing style and ability, to group constituent strokes/segments into semantically meaningful obje...
Subspace clustering methods based on data self-expression have become very popular for learning from data that lie in a union of low-dimensional linear subspaces. However, the applicability of subspace clustering has been limited because practical visual data in raw form do not necessarily lie in such linear subspaces. On the other hand, while Convolutional Neural Network (ConvNet) has been demonstrated to be a powerful tool for extracting discriminative features from visual data, training such ...
Jan 1, 2019 in CVPR (Computer Vision and Pattern Recognition)
#1Kaiyue Pang (University of Surrey)H-Index: 6
#2Ke Li (University of Surrey)H-Index: 4
Last.Yi-Zhe Song (University of Surrey)H-Index: 22
view all 7 authors...
Fine-grained sketch-based image retrieval (FG-SBIR) addresses matching specific photo instance using free-hand sketch as a query modality. Existing models aim to learn an embedding space in which sketch and photo can be directly compared. While successful, they require instance-level pairing within each coarse-grained category as annotated training data. Since the learned embedding space is domain-specific, these models do not generalise well across categories. This limits the practical applicab...
Oct 7, 2018 in ECCV (European Conference on Computer Vision)
#1Ke Li (Beijing University of Posts and Telecommunications)H-Index: 4
#2Kaiyue Pang (QMUL: Queen Mary University of London)H-Index: 6
Last.Honggang Zhang (Beijing University of Posts and Telecommunications)H-Index: 14
view all 7 authors...
In this work we aim to develop a universal sketch grouper. That is, a grouper that can be applied to sketches of any category in any domain to group constituent strokes/segments into semantically meaningful object parts. The first obstacle to this goal is the lack of large-scale datasets with grouping annotation. To overcome this, we contribute the largest sketch perceptual grouping (SPG) dataset to date, consisting of 20, 000 unique sketches evenly distributed over 25 object categories. Further...
#1Yue Zhong (Beijing University of Posts and Telecommunications)H-Index: 1
#2Honggang Zhang (Beijing University of Posts and Telecommunications)H-Index: 14
Last.Yi-Zhe Song (QMUL: Queen Mary University of London)H-Index: 22
view all 4 authors...
We propose a novel Directional Element Histogram of Oriented Gradient (DE-HOG) feature to human free-hand sketch recognition task that achieves superior performance to traditional HOG feature, originally designed for photographic objects. As a result of modeling the unique characteristics of free-hand sketch, i.e. consisting only a set of strokes omitting visual information such as color and brightness, being highly iconic and abstract. Specifically, we encode sketching strokes as a form of regu...
Jul 1, 2018 in SMC (Systems, Man and Cybernetics)
#1Jianlou Si (Beijing University of Posts and Telecommunications)H-Index: 4
#2Honggang Zhang (Beijing University of Posts and Telecommunications)H-Index: 14
Last.Jun Guo (Beijing University of Posts and Telecommunications)H-Index: 20
view all 4 authors...
Person re-identification (Re-Id) across nonoverlapping camera views is one of challenging problems in surveillance video analysis. The difficulties in person Re-Id mainly come from the large appearance variations caused by camera view angle, human pose, illumination, and occlusion. Recently, extensive efforts have been cast into addressing this problem by developing invariant features or discriminative distance metrics. However, there is still a lack of systematic evaluations on the pipeline for...
#1Jianlou SiH-Index: 4
#2Honggang ZhangH-Index: 14
Last.Gang WangH-Index: 45
view all 7 authors...
Typical person re-identification (ReID) methods usually describe each pedestrian with a single feature vector and match them in a task-specific metric space. However, the methods based on a single feature vector are not sufficient enough to overcome visual ambiguity, which frequently occurs in real scenario. In this paper, we propose a novel end-to-end trainable framework, called Dual ATtention Matching network (DuATM), to learn context-aware feature sequences and perform attentive sequence comp...
#1Shuai Di (Beijing University of Posts and Telecommunications)H-Index: 1
#2Honggang Zhang (Beijing University of Posts and Telecommunications)H-Index: 14
Last.Haibin Ling (TU: Temple University)H-Index: 47
view all 6 authors...
Understanding traffic scene images taken from vehicle mounted cameras is important for high-level tasks, such as advanced driver assistance systems and autonomous driving. It is a challenging problem due to large variations under different weather or illumination conditions. In this paper, we tackle the problem of traffic scene understanding from a cross-domain perspective. We attempt to understand the traffic scene from images taken from the same location but under different weather or illumina...
#1Ke LiH-Index: 4
#2Kaiyue PangH-Index: 6
Last.Honggang ZhangH-Index: 14
view all 7 authors...
In this work we aim to develop a universal sketch grouper. That is, a grouper that can be applied to sketches of any category in any domain to group constituent strokes/segments into semantically meaningful object parts. The first obstacle to this goal is the lack of large-scale datasets with grouping annotation. To overcome this, we contribute the largest sketch perceptual grouping (SPG) dataset to date, consisting of 20,000 unique sketches evenly distributed over 25 object categories. Furtherm...
12345678