{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/a-unified-rgb-t-saliency-detection-benchmark","title":"A Unified RGB-T Saliency Detection Benchmark: Dataset, Baselines, Analysis and A Novel Approach","arxiv_id":"1701.02829","date":"2017-01-11","proceeding":null,"authors":["Chenglong Li","Guizhao Wang","Yunpeng Ma","Aihua Zheng","Bin Luo","Jin Tang"],"abstract":"Despite significant progress, image saliency detection still remains a\nchallenging task in complex scenes and environments. Integrating multiple\ndifferent but complementary cues, like RGB and Thermal (RGB-T), may be an\neffective way for boosting saliency detection performance. The current research\nin this direction, however, is limited by the lack of a comprehensive\nbenchmark. This work contributes such a RGB-T image dataset, which includes 821\nspatially aligned RGB-T image pairs and their ground truth annotations for\nsaliency detection purpose. The image pairs are with high diversity recorded\nunder different scenes and environmental conditions, and we annotate 11\nchallenges on these image pairs for performing the challenge-sensitive analysis\nfor different saliency detection algorithms. We also implement 3 kinds of\nbaseline methods with different modality inputs to provide a comprehensive\ncomparison platform.\n  With this benchmark, we propose a novel approach, multi-task manifold ranking\nwith cross-modality consistency, for RGB-T saliency detection. In particular,\nwe introduce a weight for each modality to describe the reliability, and\nintegrate them into the graph-based manifold ranking algorithm to achieve\nadaptive fusion of different source data. Moreover, we incorporate the\ncross-modality consistent constraints to integrate different modalities\ncollaboratively. For the optimization, we design an efficient algorithm to\niteratively solve several subproblems with closed-form solutions. Extensive\nexperiments against other baseline methods on the newly created benchmark\ndemonstrate the effectiveness of the proposed approach, and we also provide\nbasic insights and potential future research directions for RGB-T saliency\ndetection.","url_abs":"http://arxiv.org/abs/1701.02829v1","url_pdf":"http://arxiv.org/pdf/1701.02829v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"a-unified-rgb-t-saliency-detection-benchmark","repo_url":"https://github.com/jxr326/swinmcnet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"saliency-detection","task_name":"Saliency Detection"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1701.02829","atlas_url":"https://app.syntology.ai/?focus=1701.02829","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}