67 citations · 330 across the 26 of their papers we have counts for
26 papers
Dual Contrastive Network for Few-Shot Remote Sensing Image Scene Classification
Zhong Ji, Liyuan Hou, Xuan Wang +2
Few-shot remote sensing image scene classification (FS-RSISC) aims at classifying remote sensing images with only a few labeled samples. The main challenges lie in small inter-clas…
Hierarchical Matching and Reasoning for Multi-Query Image Retrieval
Zhong Ji, Zhihao Li, Yan Zhang +3
As a promising field, Multi-Query Image Retrieval (MQIR) aims at searching for the semantically relevant image given multiple region-specific text queries. Existing works mainly fo…
USER: Unified Semantic Enhancement with Momentum Contrast for Image-Text Retrieval
Yan Zhang, Zhong Ji, Di Wang +2
As a fundamental and challenging task in bridging language and vision domains, Image-Text Retrieval (ITR) aims at searching for the target instances that are semantically relevant…
Memorizing Complementation Network for Few-Shot Class-Incremental Learning
Zhong Ji, Zhishen Hou, Xiyao Liu +2
Few-shot Class-Incremental Learning (FSCIL) aims at learning new concepts continually with only a few samples, which is prone to suffer the catastrophic forgetting and overfitting…
Boosting Video-Text Retrieval with Explicit High-Level Semantics
Haoran Wang, Di Xu, Dongliang He +4
Video-text retrieval (VTR) is an attractive yet challenging task for multi-modal understanding, which aims to search for relevant video (text) given a query (video). Existing metho…
CODER: Coupled Diversity-Sensitive Momentum Contrastive Learning for Image-Text Retrieval
Haoran Wang, Dongliang He, Wenhao Wu +7
Image-Text Retrieval (ITR) is challenging in bridging visual and lingual modalities. Contrastive learning has been adopted by most prior arts. Except for limited amount of negative…
Reinforced Pedestrian Attribute Recognition with Group Optimization Reward
Zhong Ji, Zhenfei Hu, Yaodong Wang +1
Pedestrian Attribute Recognition (PAR) is a challenging task in intelligent video surveillance. Two key challenges in PAR include complex alignment relations between images and att…
Self-Taught Cross-Domain Few-Shot Learning with Weakly Supervised Object Localization and Task-Decomposition
Xiyao Liu, Zhong Ji, Yanwei Pang +1
The domain shift between the source and target domain is the main challenge in Cross-Domain Few-Shot Learning (CD-FSL). However, the target domain is absolutely unknown during the…
Information Symmetry Matters: A Modal-Alternating Propagation Network for Few-Shot Learning
Zhong Ji, Zhishen Hou, Xiyao Liu +2
Semantic information provides intra-class consistency and inter-class discriminability beyond visual concepts, which has been employed in Few-Shot Learning (FSL) to achieve further…
Complementary Calibration: Boosting General Continual Learning with Collaborative Distillation and Self-Supervision
Zhong Ji, Jin Li, Qiang Wang +1
General Continual Learning (GCL) aims at learning from non independent and identically distributed stream data without catastrophic forgetting of the old tasks that don't rely on t…
Step-Wise Hierarchical Alignment Network for Image-Text Matching
Zhong Ji, Kexin Chen, Haoran Wang
Image-text matching plays a central role in bridging the semantic gap between vision and language. The key point to achieve precise visual-semantic alignment lies in capturing the…
Consensus-Aware Visual-Semantic Embedding for Image-Text Matching
Haoran Wang, Ying Zhang, Zhong Ji +2
Image-text matching plays a central role in bridging vision and language. Most existing approaches only rely on the image-text instance pair to learn their representations, thereby…
GTNet: Generative Transfer Network for Zero-Shot Object Detection
Shizhen Zhao, Changxin Gao, Yuanjie Shao +4
We propose a Generative Transfer Network (GTNet) for zero shot object detection (ZSD). GTNet consists of an Object Detection Module and a Knowledge Transfer Module. The Object Dete…
Episode-based Prototype Generating Network for Zero-Shot Learning
Yunlong Yu, Zhong Ji, Zhongfei Zhang +1
We introduce a simple yet effective episode-based training framework for zero-shot learning (ZSL), where the learning system requires to recognize unseen classes given only the cor…
A Semantics-Guided Class Imbalance Learning Model for Zero-Shot Classification
Zhong Ji, Xuejie Yu, Yunlong Yu +2
Zero-Shot Classification (ZSC) equips the learned model with the ability to recognize the visual instances from the novel classes via constructing the interactions between the visu…
Saliency-Guided Attention Network for Image-Sentence Matching
Zhong Ji, Haoran Wang, Jungong Han +1
This paper studies the task of matching image and sentence, where learning appropriate representations across the multi-modal data appears to be the main challenge. Unlike previous…
Bi-Adversarial Auto-Encoder for Zero-Shot Learning
Yunlong Yu, Zhong Ji, Yanwei Pang +3
Existing generative Zero-Shot Learning (ZSL) methods only consider the unidirectional alignment from the class semantics to the visual features while ignoring the alignment from th…
Stacked Semantic-Guided Attention Model for Fine-Grained Zero-Shot Learning
Yunlong Yu, Zhong Ji, Yanwei Fu +3
Zero-Shot Learning (ZSL) is achieved via aligning the semantic relationships between the global image feature vector and the corresponding class semantic descriptions. However, usi…
Attribute-Guided Network for Cross-Modal Zero-Shot Hashing
Zhong Ji, Yuxin Sun, Yunlong Yu +2
Zero-Shot Hashing aims at learning a hashing model that is trained only by instances from seen categories but can generate well to those of unseen categories. Typically, it is achi…
Zero-Shot Learning via Latent Space Encoding
Yunlong Yu, Zhong Ji, Jichang Guo +2
Zero-Shot Learning (ZSL) is typically achieved by resorting to a class semantic embedding space to transfer the knowledge from the seen classes to unseen ones. Capturing the common…
Video Summarization with Attention-Based Encoder-Decoder Networks
Zhong Ji, Kailin Xiong, Yanwei Pang +1
This paper addresses the problem of supervised video summarization by formulating it as a sequence-to-sequence learning problem, where the input is a sequence of original video fra…
Query-Aware Sparse Coding for Multi-Video Summarization
Zhong Ji, Yaru Ma, Yanwei Pang +1
Given the explosive growth of online videos, it is becoming increasingly important to relieve the tedious work of browsing and managing the video content of interest. Video summari…
Semantic Softmax Loss for Zero-Shot Learning
Zhong Ji, Yunxin Sun, Yulong Yu +2
A typical pipeline for Zero-Shot Learning (ZSL) is to integrate the visual features and the class semantic descriptors into a multimodal framework with a linear or bilinear model.…
Transductive Zero-Shot Learning with Adaptive Structural Embedding
Yunlong Yu, Zhong Ji, Jichang Guo +1
Zero-shot learning (ZSL) endows the computer vision system with the inferential capability to recognize instances of a new category that has never seen before. Two fundamental chal…