Jianghang Lin
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Jianghang Lin has a total of 25 co-authors. Here are the top co-authors by number of shared publications:
- Liujuan Cao
Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, Xiamen, Fujian, China
8 shared publications - Jiayi Ji
Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, Xiamen, China
4 shared publications - Rongrong Ji
Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, Xiamen, China
4 shared publications - Shengchuan Zhang
Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, Xiamen, Fujian, China
4 shared publications - Kai Ye
Xiamen University, Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen, China
3 shared publications - Pingyang Dai
Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, Xiamen, China
3 shared publications
Latest Publications
- Open Access
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 13542-13550
Evolving, Not Training: Training-Free Reasoning Segmentation via Evolutionary Prompting
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 13542-13550
Open AccessEvolving, Not Training: Training-Free Reasoning Segmentation via Evolutionary Prompting
- Open Access
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 2654-2663
HieraVid: Hierarchical Token Pruning for Fast Video Large Language Models
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 2654-2663
Open AccessHieraVid: Hierarchical Token Pruning for Fast Video Large Language Models
- Open Access
Evolving, Not Training: Zero-Shot Reasoning Segmentation via Evolutionary Prompting
Reasoning Segmentation requires models to interpret complex, context-dependent linguistic queries to achieve pixel-level localization. Current dominant approaches rely heavily on Supervised Fine-Tuning (SFT) or Reinforcement Learning (RL). However, SFT suffers from catastrophic forgetting and domain dependency, while RL is often hindered by training instability and rigid reliance on predefined reward functions. Although recent training-free methods circumvent these training burdens, they are fundamentally limited by a static inference paradigm. These methods typically rely on a single-pass "generate-then-segment" chain, which suffers from insufficient reasoning depth and lacks the capability to self-correct linguistic hallucinations or spatial misinterpretations. In this paper, we challenge these limitations and propose EVOL-SAM3, a novel zero-shot framework that reformulates reasoning segmentation as an inference-time evolutionary search process. Instead of relying on a fixed prompt, EVOL-SAM3 maintains a population of prompt hypotheses and iteratively refines them through a "Generate-Evaluate-Evolve" loop. We introduce a Visual Arena to assess prompt fitness via reference-free pairwise tournaments, and a Semantic Mutation operator to inject diversity and correct semantic errors. Furthermore, a Heterogeneous Arena module integrates geometric priors with semantic reasoning to ensure robust final selection. Extensive experiments demonstrate that EVOL-SAM3 not only substantially outperforms static baselines but also significantly surpasses fully supervised state-of-the-art methods on the challenging ReasonSeg benchmark in a zero-shot setting. The code is available at https://github.com/AHideoKuzeA/Evol-SAM3.
Open AccessEvolving, Not Training: Zero-Shot Reasoning Segmentation via Evolutionary Prompting
Reasoning Segmentation requires models to interpret complex, context-dependent linguistic queries to achieve pixel-level localization. Current dominant approaches rely heavily on Supervised Fine-Tuning (SFT) or Reinforcement Learning (RL). However, SFT suffers from catastrophic forgetting and domain dependency, while RL is often hindered by training instability and rigid reliance on predefined reward functions. Although recent training-free methods circumvent these training burdens, they are fundamentally limited by a static inference paradigm. These methods typically rely on a single-pass "generate-then-segment" chain, which suffers from insufficient reasoning depth and lacks the capability to self-correct linguistic hallucinations or spatial misinterpretations. In this paper, we challenge these limitations and propose EVOL-SAM3, a novel zero-shot framework that reformulates reasoning segmentation as an inference-time evolutionary search process. Instead of relying on a fixed prompt, EVOL-SAM3 maintains a population of prompt hypotheses and iteratively refines them through a "Generate-Evaluate-Evolve" loop. We introduce a Visual Arena to assess prompt fitness via reference-free pairwise tournaments, and a Semantic Mutation operator to inject diversity and correct semantic errors. Furthermore, a Heterogeneous Arena module integrates geometric priors with semantic reasoning to ensure robust final selection. Extensive experiments demonstrate that EVOL-SAM3 not only substantially outperforms static baselines but also significantly surpasses fully supervised state-of-the-art methods on the challenging ReasonSeg benchmark in a zero-shot setting. The code is available at https://github.com/AHideoKuzeA/Evol-SAM3.
- Open Access
- 27 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 11259-11268
Generate Aligned Anomaly: Region-Guided Few-Shot Anomaly Image-Mask Pair Synthesis for Industrial Inspection
- 27 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 11259-11268
Open AccessGenerate Aligned Anomaly: Region-Guided Few-Shot Anomaly Image-Mask Pair Synthesis for Industrial Inspection
- Open Access
- 27 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 2841-2850
What You Perceive Is What You Conceive: A Cognition-Inspired Framework for Open Vocabulary Image Segmentation
- 27 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 2841-2850
Open AccessWhat You Perceive Is What You Conceive: A Cognition-Inspired Framework for Open Vocabulary Image Segmentation
- Open Access
Understanding What Is Not Said:Referring Remote Sensing Image Segmentation with Scarce Expressions
Referring Remote Sensing Image Segmentation (RRSIS) aims to segment instances in remote sensing images according to referring expressions. Unlike Referring Image Segmentation on general images, acquiring high-quality referring expressions in the remote sensing domain is particularly challenging due to the prevalence of small, densely distributed objects and complex backgrounds. This paper introduces a new learning paradigm, Weakly Referring Expression Learning (WREL) for RRSIS, which leverages abundant class names as weakly referring expressions together with a small set of accurate ones to enable efficient training under limited annotation conditions. Furthermore, we provide a theoretical analysis showing that mixed-referring training yields a provable upper bound on the performance gap relative to training with fully annotated referring expressions, thereby establishing the validity of this new setting. We also propose LRB-WREL, which integrates a Learnable Reference Bank (LRB) to refine weakly referring expressions through sample-specific prompt embeddings that enrich coarse class-name inputs. Combined with a teacher-student optimization framework using dynamically scheduled EMA updates, LRB-WREL stabilizes training and enhances cross-modal generalization under noisy weakly referring supervision. Extensive experiments on our newly constructed benchmark with varying weakly referring data ratios validate both the theoretical insights and the practical effectiveness of WREL and LRB-WREL, demonstrating that they can approach or even surpass models trained with fully annotated referring expressions.
Open AccessUnderstanding What Is Not Said:Referring Remote Sensing Image Segmentation with Scarce Expressions
Referring Remote Sensing Image Segmentation (RRSIS) aims to segment instances in remote sensing images according to referring expressions. Unlike Referring Image Segmentation on general images, acquiring high-quality referring expressions in the remote sensing domain is particularly challenging due to the prevalence of small, densely distributed objects and complex backgrounds. This paper introduces a new learning paradigm, Weakly Referring Expression Learning (WREL) for RRSIS, which leverages abundant class names as weakly referring expressions together with a small set of accurate ones to enable efficient training under limited annotation conditions. Furthermore, we provide a theoretical analysis showing that mixed-referring training yields a provable upper bound on the performance gap relative to training with fully annotated referring expressions, thereby establishing the validity of this new setting. We also propose LRB-WREL, which integrates a Learnable Reference Bank (LRB) to refine weakly referring expressions through sample-specific prompt embeddings that enrich coarse class-name inputs. Combined with a teacher-student optimization framework using dynamically scheduled EMA updates, LRB-WREL stabilizes training and enhances cross-modal generalization under noisy weakly referring supervision. Extensive experiments on our newly constructed benchmark with varying weakly referring data ratios validate both the theoretical insights and the practical effectiveness of WREL and LRB-WREL, demonstrating that they can approach or even surpass models trained with fully annotated referring expressions.
- Open Access
- 28 October 2024
- Published by Association for Computing Machinery (ACM)
- p. 5328-5337
GOI: Find 3D Gaussians of Interest with an Optimizable Open-vocabulary Semantic-space Hyperplane
3D open-vocabulary scene understanding, crucial for advancing augmented reality and robotic applications, involves interpreting and locating specific regions within a 3D space as directed by natural language instructions. To this end, we introduce GOI, a framework that integrates semantic features from 2D vision-language foundation models into 3D Gaussian Splatting (3DGS) and identifies 3D Gaussians of Interest using an Optimizable Semantic-space Hyperplane. Our approach includes an efficient compression method that utilizes scene priors to condense noisy high-dimensional semantic features into compact low-dimensional vectors, which are subsequently embedded in 3DGS. During the open-vocabulary querying process, we adopt a distinct approach compared to existing methods, which depend on a manually set fixed empirical threshold to select regions based on their semantic feature distance to the query text embedding. This traditional approach often lacks universal accuracy, leading to challenges in precisely identifying specific target areas. Instead, our method treats the feature selection process as a hyperplane division within the feature space, retaining only those features that are highly relevant to the query. We leverage off-the-shelf 2D Referring Expression Segmentation (RES) models to fine-tune the semantic-space hyperplane, enabling a more precise distinction between target regions and others. This fine-tuning substantially improves the accuracy of open-vocabulary queries, ensuring the precise localization of pertinent 3D Gaussians. Extensive experiments demonstrate GOI's superiority over previous state-of-the-art methods. The dataset, model, and code are available at https://quyans.github.io/GOI-Hyperplane/.
- 28 October 2024
- Published by Association for Computing Machinery (ACM)
- p. 5328-5337
Open AccessGOI: Find 3D Gaussians of Interest with an Optimizable Open-vocabulary Semantic-space Hyperplane
3D open-vocabulary scene understanding, crucial for advancing augmented reality and robotic applications, involves interpreting and locating specific regions within a 3D space as directed by natural language instructions. To this end, we introduce GOI, a framework that integrates semantic features from 2D vision-language foundation models into 3D Gaussian Splatting (3DGS) and identifies 3D Gaussians of Interest using an Optimizable Semantic-space Hyperplane. Our approach includes an efficient compression method that utilizes scene priors to condense noisy high-dimensional semantic features into compact low-dimensional vectors, which are subsequently embedded in 3DGS. During the open-vocabulary querying process, we adopt a distinct approach compared to existing methods, which depend on a manually set fixed empirical threshold to select regions based on their semantic feature distance to the query text embedding. This traditional approach often lacks universal accuracy, leading to challenges in precisely identifying specific target areas. Instead, our method treats the feature selection process as a hyperplane division within the feature space, retaining only those features that are highly relevant to the query. We leverage off-the-shelf 2D Referring Expression Segmentation (RES) models to fine-tune the semantic-space hyperplane, enabling a more precise distinction between target regions and others. This fine-tuning substantially improves the accuracy of open-vocabulary queries, ensuring the precise localization of pertinent 3D Gaussians. Extensive experiments demonstrate GOI's superiority over previous state-of-the-art methods. The dataset, model, and code are available at https://quyans.github.io/GOI-Hyperplane/.
- Open Access
- 28 October 2024
- Published by Association for Computing Machinery (ACM)
- p. 1101-1110
Adaptive Selection based Referring Image Segmentation
Referring image segmentation (RIS) aims to segment a particular region based on a specific expression. Existing one-stage methods have explored various fusion strategies, yet they encounter two significant issues. Primarily, most methods rely on manually selected visual features from the visual encoder layers. Moreover, the direct fusion of word-level features into coarse aligned features disrupts the established vision-language alignment. In this paper, we introduce an innovative framework for RIS that seeks to overcome these challenges with adaptive alignment of vision and language features, termed the Adaptive Selection with Dual Alignment (ASDA). ASDA innovates in two aspects. Firstly, we design an Adaptive Feature Selection and Fusion (AFSF) module to dynamically select visual features focusing on different regions related to various descriptions. AFSF is equipped with scale-wise feature aggregator to provide hierarchically coarse features that preserve crucial low-level details. Secondly, a Word Guided Dual-Branch Aligner (WGDA) is leveraged to integrate coarse features with linguistic cues by word-guided attention, which effectively addresses the common issue of vision-language misalignment. Extensive experimental results demonstrate that our ASDA framework surpasses state-of-the-art methods on RefCOCO, RefCOCO+ and G-Ref benchmark.
- 28 October 2024
- Published by Association for Computing Machinery (ACM)
- p. 1101-1110
Open AccessAdaptive Selection based Referring Image Segmentation
Referring image segmentation (RIS) aims to segment a particular region based on a specific expression. Existing one-stage methods have explored various fusion strategies, yet they encounter two significant issues. Primarily, most methods rely on manually selected visual features from the visual encoder layers. Moreover, the direct fusion of word-level features into coarse aligned features disrupts the established vision-language alignment. In this paper, we introduce an innovative framework for RIS that seeks to overcome these challenges with adaptive alignment of vision and language features, termed the Adaptive Selection with Dual Alignment (ASDA). ASDA innovates in two aspects. Firstly, we design an Adaptive Feature Selection and Fusion (AFSF) module to dynamically select visual features focusing on different regions related to various descriptions. AFSF is equipped with scale-wise feature aggregator to provide hierarchically coarse features that preserve crucial low-level details. Secondly, a Word Guided Dual-Branch Aligner (WGDA) is leveraged to integrate coarse features with linguistic cues by word-guided attention, which effectively addresses the common issue of vision-language misalignment. Extensive experimental results demonstrate that our ASDA framework surpasses state-of-the-art methods on RefCOCO, RefCOCO+ and G-Ref benchmark.