Long Li
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
Long Li has a total of 19 co-authors. Here are the top co-authors by number of shared publications:
- Nian Liu
Mohamed bin Zayed University of Artificial Intelligence
5 shared publications - Junwei Han
School of Artificial Intelligence, Chongqing University of Posts and Telecommunications, Chongqing, China
4 shared publications - Hisham Cholakkal
Mohamed bin Zayed University of Artificial Intelligence
3 shared publications - Rao Muhammad Anwer
Mohamed bin Zayed University of Artificial Intelligence
3 shared publications - Dingwen Zhang
Institute of Artificial Intelligence, Hefei Comprehensive National Science Center, Hefei, China
2 shared publications - Fahad Shahbaz Khan
Mohamed bin Zayed University of Artificial Intelligence, Abu Dhabi, United Arab Emirates
2 shared publications
Latest Publications
- 23 May 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 47 (9) , 7733-7751
Advanced Discriminative Co-Saliency and Background Mining Transformer for Co-Salient Object Detection
Most existing CoSOD models focus solely on extracting co-saliency cues while neglecting explicit exploration of background regions, potentially leading to difficulties in handling interference from complex background areas. To address this, this paper proposes a Discriminative co-saliency and background Mining Transformer framework (DMT) to explicitly mine both co-saliency and background information and effectively model their discriminability. DMT first learns two types of tokens by disjointly extracting co-saliency and background information from segmentation features, then performs discriminability within the segmentation features guided by these well-learned tokens. In the first phase, we propose economic multi-grained correlation modules for efficient detection information extraction, including Region-to-Region (R2R), Contrast-induced Pixel-to-Token (CtP2T), and Co-saliency Token-to-Token (CoT2T) correlation modules. In the subsequent phase, we introduce Token-Guided Feature Refinement (TGFR) modules to enhance discriminability within the segmentation features. To further enhance the discriminative modeling and practicality of DMT, we first upgrade the original TGFR’s intra-image modeling approach to an intra-group one, thus proposing Group TGFR (G-TGFR), which is more suitable for the co-saliency task. Subsequently, we designed a Noise Propagation Suppression (NPS) mechanism to apply our model to a more practical open-world scenario, ultimately presenting our extended version, i.e. DMT+O. Extensive experimental results on both conventional CoSOD and open-world CoSOD benchmark datasets demonstrate the effectiveness of our proposed model.
- 23 May 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 47 (9) , 7733-7751
Advanced Discriminative Co-Saliency and Background Mining Transformer for Co-Salient Object Detection
Most existing CoSOD models focus solely on extracting co-saliency cues while neglecting explicit exploration of background regions, potentially leading to difficulties in handling interference from complex background areas. To address this, this paper proposes a Discriminative co-saliency and background Mining Transformer framework (DMT) to explicitly mine both co-saliency and background information and effectively model their discriminability. DMT first learns two types of tokens by disjointly extracting co-saliency and background information from segmentation features, then performs discriminability within the segmentation features guided by these well-learned tokens. In the first phase, we propose economic multi-grained correlation modules for efficient detection information extraction, including Region-to-Region (R2R), Contrast-induced Pixel-to-Token (CtP2T), and Co-saliency Token-to-Token (CoT2T) correlation modules. In the subsequent phase, we introduce Token-Guided Feature Refinement (TGFR) modules to enhance discriminability within the segmentation features. To further enhance the discriminative modeling and practicality of DMT, we first upgrade the original TGFR’s intra-image modeling approach to an intra-group one, thus proposing Group TGFR (G-TGFR), which is more suitable for the co-saliency task. Subsequently, we designed a Noise Propagation Suppression (NPS) mechanism to apply our model to a more practical open-world scenario, ultimately presenting our extended version, i.e. DMT+O. Extensive experimental results on both conventional CoSOD and open-world CoSOD benchmark datasets demonstrate the effectiveness of our proposed model.
- 1 November 2024
- Published by Springer Nature
- p. 287-303
CONDA: Condensed Deep Association Learning for Co-salient Object Detection
- 1 November 2024
- Published by Springer Nature
- p. 287-303
CONDA: Condensed Deep Association Learning for Co-salient Object Detection
- 19 October 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 46 (1) , 479-496
Robust Perception and Precise Segmentation for Scribble-Supervised RGB-D Saliency Detection
This paper proposes a scribble-based weakly supervised RGB-D salient object detection (SOD) method to relieve the annotation burden from pixel-wise annotations. In view of the ensuing performance drop, we summarize two natural deficiencies of the scribbles and try to alleviate them, which are the weak richness of the pixel training samples (WRPS) and the poor structural integrity of the salient objects (PSIO). WRPS hinders robust saliency perception learning, which can be alleviated via model design for robust feature learning and pseudo labels generation for training sample enrichment. Specifically, we first design a dynamic searching process module as a meta operation to conduct multi-scale and multi-modal feature fusion for the robust RGB-D SOD model construction. Then, a dual-branch consistency learning mechanism is proposed to generate enough pixel training samples for robust saliency perception learning. PSIO makes direct structural learning infeasible since scribbles can not provide integral structural supervision. Thus, we propose an edge-region structure-refinement loss to recover the structural information and make precise segmentation. We deploy all components and conduct ablation studies on two baselines to validate their effectiveness and generalizability. Experimental results on eight datasets show that our method outperforms other scribble-based SOD models and achieves comparable performance with fully supervised state-of-the-art methods.
- 19 October 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 46 (1) , 479-496
Robust Perception and Precise Segmentation for Scribble-Supervised RGB-D Saliency Detection
This paper proposes a scribble-based weakly supervised RGB-D salient object detection (SOD) method to relieve the annotation burden from pixel-wise annotations. In view of the ensuing performance drop, we summarize two natural deficiencies of the scribbles and try to alleviate them, which are the weak richness of the pixel training samples (WRPS) and the poor structural integrity of the salient objects (PSIO). WRPS hinders robust saliency perception learning, which can be alleviated via model design for robust feature learning and pseudo labels generation for training sample enrichment. Specifically, we first design a dynamic searching process module as a meta operation to conduct multi-scale and multi-modal feature fusion for the robust RGB-D SOD model construction. Then, a dual-branch consistency learning mechanism is proposed to generate enough pixel training samples for robust saliency perception learning. PSIO makes direct structural learning infeasible since scribbles can not provide integral structural supervision. Thus, we propose an edge-region structure-refinement loss to recover the structural information and make precise segmentation. We deploy all components and conduct ablation studies on two baselines to validate their effectiveness and generalizability. Experimental results on eight datasets show that our method outperforms other scribble-based SOD models and achieves comparable performance with fully supervised state-of-the-art methods.
- 1 February 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 342-345
Autonomous Obstacle Avoidance Method for Substation Inspection Robot Based on Binocular Vision
In order to effectively solve the problems of robot path deviation and long obstacle avoidance path, an autonomous obstacle avoidance method for substation inspection robot based on binocular vision is proposed. The model of binocular stereo vision system is constructed, the three-dimensional world coordinate system of space points is obtained, and the position, distance, shape and other information of obstacles are obtained; After obtaining the position information of the obstacle, the vector field histogram algorithm (VFH) is used to adjust the robot's moving direction to achieve autonomous obstacle avoidance. The experimental results show that the success rate of obstacle avoidance of the proposed method is 96%, the obstacle avoidance path is short, and there is no deviation problem, which verifies its application effect.
- 1 February 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 342-345
Autonomous Obstacle Avoidance Method for Substation Inspection Robot Based on Binocular Vision
In order to effectively solve the problems of robot path deviation and long obstacle avoidance path, an autonomous obstacle avoidance method for substation inspection robot based on binocular vision is proposed. The model of binocular stereo vision system is constructed, the three-dimensional world coordinate system of space points is obtained, and the position, distance, shape and other information of obstacles are obtained; After obtaining the position information of the obstacle, the vector field histogram algorithm (VFH) is used to adjust the robot's moving direction to achieve autonomous obstacle avoidance. The experimental results show that the success rate of obstacle avoidance of the proposed method is 96%, the obstacle avoidance path is short, and there is no deviation problem, which verifies its application effect.
- 26 August 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. PP (01628828) , 1
Instance-Level Relative Saliency Ranking with Graph Reasoning
Conventional salient object detection models cannot differentiate the importance of different salient objects. Two works have proposed to detect saliency ranking by assigning different degrees of saliency to different objects. However, one of these models cannot differentiate object instances and the other focuses more on sequential attention shift order inference. In this paper, we investigate a practical problem setting which requires to simultaneously segment salient instances and infer their relative saliency rank order. We present a novel unified model as the first end-to-end solution, where an improved Mask R-CNN is first used to segment salient instances and a saliency ranking branch is then added to infer the relative saliency. For relative saliency ranking, we build a novel graph reasoning module by combining four graphs to incorporate the instance interaction relation, local contrast, global contrast, and a high-level semantic prior, respectively. A novel loss function is proposed to effectively train the saliency ranking branch. Besides, a new dataset and an evaluation metric are proposed for this task, aiming at pushing forward this field of research. Finally, experimental results demonstrate that our proposed model is more effective than previous methods. We show an example of its practical usage on adaptive image retargeting.
- 26 August 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. PP (01628828) , 1
Instance-Level Relative Saliency Ranking with Graph Reasoning
Conventional salient object detection models cannot differentiate the importance of different salient objects. Two works have proposed to detect saliency ranking by assigning different degrees of saliency to different objects. However, one of these models cannot differentiate object instances and the other focuses more on sequential attention shift order inference. In this paper, we investigate a practical problem setting which requires to simultaneously segment salient instances and infer their relative saliency rank order. We present a novel unified model as the first end-to-end solution, where an improved Mask R-CNN is first used to segment salient instances and a saliency ranking branch is then added to infer the relative saliency. For relative saliency ranking, we build a novel graph reasoning module by combining four graphs to incorporate the instance interaction relation, local contrast, global contrast, and a high-level semantic prior, respectively. A novel loss function is proposed to effectively train the saliency ranking branch. Besides, a new dataset and an evaluation metric are proposed for this task, aiming at pushing forward this field of research. Finally, experimental results demonstrate that our proposed model is more effective than previous methods. We show an example of its practical usage on adaptive image retargeting.
- 23 February 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. 24 (15209210) , 755-767
Deep RGB-D Saliency Detection Without Depth
The existing saliency detection models based on RGB colors only leverage appearance cues to detect salient objects. Depth information also plays a very important role in visual saliency detection and can supply complementary cues for saliency detection. Although many RGB-D saliency models have been proposed, they require to acquire depth data, which is expensive and not easy to get. In this paper, we propose to estimate depth information from monocular RGB images and leverage the intermediate depth features to enhance the saliency detection performance in a deep neural network framework. Specifically, we first use an encoder network to extract common features from each RGB image and then build two decoder networks for depth estimation and saliency detection, respectively. The depth decoder features can be fused with the RGB saliency features to enhance their capability. Furthermore, we also propose a novel dense multiscale fusion model to densely fuse multiscale depth and RGB features based on the dense ASPP model. A new global context branch is also added to boost the multiscale features. Experimental results demonstrate that the added depth cues and the proposed fusion model can both improve the saliency detection performance. Finally, our model not only outperforms state-of-the-art RGB saliency models, but also achieves comparable results compared with state-of-the-art RGB-D saliency models.
- 23 February 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. 24 (15209210) , 755-767
Deep RGB-D Saliency Detection Without Depth
The existing saliency detection models based on RGB colors only leverage appearance cues to detect salient objects. Depth information also plays a very important role in visual saliency detection and can supply complementary cues for saliency detection. Although many RGB-D saliency models have been proposed, they require to acquire depth data, which is expensive and not easy to get. In this paper, we propose to estimate depth information from monocular RGB images and leverage the intermediate depth features to enhance the saliency detection performance in a deep neural network framework. Specifically, we first use an encoder network to extract common features from each RGB image and then build two decoder networks for depth estimation and saliency detection, respectively. The depth decoder features can be fused with the RGB saliency features to enhance their capability. Furthermore, we also propose a novel dense multiscale fusion model to densely fuse multiscale depth and RGB features based on the dense ASPP model. A new global context branch is also added to boost the multiscale features. Experimental results demonstrate that the added depth cues and the proposed fusion model can both improve the saliency detection performance. Finally, our model not only outperforms state-of-the-art RGB saliency models, but also achieves comparable results compared with state-of-the-art RGB-D saliency models.