← Search

Zhiwei Chen

20 accepted papers

2026

Air-Know: Arbiter-Calibrated Knowledge-Internalizing Robust Network for Composed Image Retrieval

CVPR 2026

Composed Image Retrieval (CIR) has attracted significant attention due to its flexible multimodal query method, yet its development is severely constrained by the Noisy Triplet Correspondence (NTC) problem. Most existing robust learning methods rely on the "small loss hypothesis", but the unique sem

Cited by 0SourcecodeScholar
2026

ConeSep: Cone-based Robust Noise-Unlearning Compositional Network for Composed Image Retrieval

CVPR 2026

The Composed Image Retrieval (CIR) task provides a flexible retrieval paradigm via a reference image and modification text, but it heavily relies on expensive and error-prone triplet annotations. This paper systematically investigates the Noisy Triplet Correspondence (NTC) problem introduced by anno

Cited by 0SourcecodeScholar
2026

HABIT: Chrono-Synergia Robust Progressive Learning Framework for Composed Image Retrieval

AAAI 2026technical

Composed Image Retrieval (CIR) is a flexible image retrieval paradigm that enables users to accurately locate the target image through a multimodal query composed of a reference image and modification text. Although this task has demonstrated promising applications in personalized search and recomme

Cited by 0SourcePDFScholar
2026

INTENT: Invariance and Discrimination-aware Noise Mitigation for Robust Composed Image Retrieval

AAAI 2026technical

Composed Image Retrieval (CIR) is a challenging image retrieval paradigm that enables to retrieve target images based on multimodal queries consisting of reference images and modification texts. Although substantial progress has been made in recent years, existing methods assume that all samples are

Cited by 0SourcePDFScholar
2026

InTrain: Intrinsic Trainability for Zero-Cost Neural Architecture Search

CVPR 2026

Training-free neural architecture search promises efficient discovery of high-performance networks without costly training. However, existing zero-cost proxies rely on fragmented heuristics that fail to capture the fundamental question: what makes an architecture trainable? This paper introduces Int

Cited by 0SourceScholar
2026

NoOVD: Novel Category Discovery and Embedding for Open-Vocabulary Object Detection

CVPR 2026

Despite the remarkable progress in open-vocabulary object detection (OVD), a significant gap remains between the training and testing phases. During training, the RPN and RoI heads often misclassify unlabeled novel-category objects as background, causing some proposals to be prematurely filtered out

Cited by 0SourceScholar
2026

ReTrack: Evidence-Driven Dual-Stream Directional Anchor Calibration Network for Composed Video Retrieval

AAAI 2026technical

With the rapid growth of video data, Composed Video Retrieval (CVR) has emerged as a novel paradigm in video retrieval and is receiving increasing attention from researchers. Unlike unimodal video retrieval methods, the CVR task takes a multi-modal query consisting of a reference video and a piece o

Cited by 0SourcePDFScholar
2025

A Sequential Approach for Accurate Parameters Identification of Heavy-Duty Hydraulic Manipulators Ensuring Physical Feasibility

RA-L 2025

Accurate identification of dynamic parameters is essential for precise motion control and autonomous operation of heavy-duty hydraulic manipulators. However, due to their low-speed motion property, conventional approaches fail to simultaneously excite all parameters. To overcome this issue, a sequen

Cited by 3SourceScholar
2025

ENCODER: Entity Mining and Modification Relation Binding for Composed Image Retrieval

AAAI 2025technical

The objective of Composed Image Retrieval (CIR) is to identify a target image that meets the requirement based on a multimodal query (including the reference image and the modification text) provided by the user. Despite the notable success of existing approaches, they fail to adequately address the…

Cited by 2SourcePDFScholar
2025

MEDIAN: Adaptive Intermediate-grained Aggregation Network for Composed Image Retrieval

ICASSP 2025accepted

The Composed Image Retrieval (CIR) task aims to retrieve a target image that meets the requirements based on a given multimodal query (includes a reference image and modification text). Most existing works align multimodal semantics at both local and global granularity. However, they have failed to…

Cited by 0SourceScholar
2025

PAIR: Complementarity-guided Disentanglement for Composed Image Retrieval

ICASSP 2025accepted

Composed Image Retrieval (CIR) is a novel image retrieval paradigm that aims at searching for the target images via the multimodal query including a reference image and a modification text. Although existing works have made significant progress, they overlook the inter-modal coherence and incoherenc…

Cited by 0SourceScholar
2023

Category-aware Allocation Transformer for Weakly Supervised Object Localization

ICCV 2023poster

Weakly supervised object localization (WSOL) aims to localize objects based on only image-level labels as supervision. Recently, transformers have been introduced into WSOL, yielding impressive results. The self-attention mechanism and multilayer perceptron structure in transformers preserve long-ra…

Cited by 15PDFScholar
2022

LCTR: On Awakening the Local Continuity of Transformer for Weakly Supervised Object Localization

AAAI 2022technical

Weakly supervised object localization (WSOL) aims to learn object localizer solely by using image-level labels. The convolution neural network (CNN) based techniques often result in highlighting the most discriminative part of objects while ignoring the entire object extent. Recently, the transforme…

Cited by 57SourcePDFScholar
2022

PCBERT: Parent and Child BERT for Chinese Few-shot NER

COLING 2022main

Achieving good performance on few-shot or zero-shot datasets has been a long-term challenge for NER. The conventional semantic transfer approaches on NER will decrease model performance when the semantic distribution is quite different, especially in Chinese few-shot NER. Recently, prompt-tuning has…

Cited by 13SourcePDFScholar
2021

Parallel Detection-and-Segmentation Learning for Weakly Supervised Instance Segmentation

ICCV 2021poster

Weakly supervised instance segmentation (WSIS) with only image-level labels has recently drawn much attention. To date, bottom-up WSIS methods refine discriminative cues from classifiers with sophisticated multi-stage training procedures, which also suffer from inconsistent object boundaries. And to…

Cited by 23PDFScholar
2021

Toward Joint Thing-and-Stuff Mining for Weakly Supervised Panoptic Segmentation

CVPR 2021poster

Panoptic segmentation aims to partition an image to object instances and semantic content for thing and stuff categories, respectively. To date, learning weakly supervised panoptic segmentation (WSPS) with only image-level labels remains unexplored. In this paper, we propose an efficient jointly thi…

Cited by 19PDFScholar
2020

Enabling Deep Residual Networks for Weakly Supervised Object Detection

ECCV 2020poster

Weakly supervised object detection (WSOD) has attracted extensive research attention due to its great flexibility of exploiting large-scale image-level annotation for detector training. Whilst deep residual networks such as ResNet and DenseNet have become the standard backbones for many computer vis…

Cited by 59SourcePDFScholar
2020

Noise-Aware Fully Webly Supervised Object Detection

CVPR 2020poster

We investigate the emerging task of learning object detectors with sole image-level labels on the web without requiring any other supervision like precise annotations or additional images from well-annotated benchmark datasets. Such a task, termed as fully webly supervised object detection, is extre…

Cited by 40PDFScholar
2020

UWSOD: Toward Fully-Supervised-Level Capacity Weakly Supervised Object Detection

NeurIPS 2020poster

Weakly supervised object detection (WSOD) has attracted extensive research attention due to its great flexibility of exploiting large-scale dataset with only image-level annotations for detector training. Despite its great advance in recent years, WSOD still suffers limited performance, which is far…