{"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-deep-spatial-contextual-long-term-recurrent","title":"A Deep Spatial Contextual Long-term Recurrent Convolutional Network for Saliency Detection","arxiv_id":"1610.01708","date":"2016-10-06","proceeding":null,"authors":["Nian Liu","Junwei Han"],"abstract":"Traditional saliency models usually adopt hand-crafted image features and\nhuman-designed mechanisms to calculate local or global contrast. In this paper,\nwe propose a novel computational saliency model, i.e., deep spatial contextual\nlong-term recurrent convolutional network (DSCLRCN) to predict where people\nlooks in natural scenes. DSCLRCN first automatically learns saliency related\nlocal features on each image location in parallel. Then, in contrast with most\nother deep network based saliency models which infer saliency in local\ncontexts, DSCLRCN can mimic the cortical lateral inhibition mechanisms in human\nvisual system to incorporate global contexts to assess the saliency of each\nimage location by leveraging the deep spatial long short-term memory (DSLSTM)\nmodel. Moreover, we also integrate scene context modulation in DSLSTM for\nsaliency inference, leading to a novel deep spatial contextual LSTM (DSCLSTM)\nmodel. The whole network can be trained end-to-end and works efficiently when\ntesting. Experimental results on two benchmark datasets show that DSCLRCN can\nachieve state-of-the-art performance on saliency detection. Furthermore, the\nproposed DSCLSTM model can significantly boost the saliency detection\nperformance by incorporating both global spatial interconnections and scene\ncontext modulation, which may uncover novel inspirations for studies on them in\ncomputational saliency models.","url_abs":"http://arxiv.org/abs/1610.01708v1","url_pdf":"http://arxiv.org/pdf/1610.01708v1.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-deep-spatial-contextual-long-term-recurrent","repo_url":"https://github.com/nian-liu/DSCLRCN","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"a-deep-spatial-contextual-long-term-recurrent","repo_url":"https://github.com/AAshqar/DSCLRCN-PyTorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"saliency-detection","task_name":"Saliency Detection"}],"methods":[{"method_slug":"lstm","method_name":"LSTM"},{"method_slug":"sigmoid-activation","method_name":"Sigmoid Activation"},{"method_slug":"tanh-activation","method_name":"Tanh Activation"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1610.01708","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1610.01708"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/nian-liu/DSCLRCN","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/AAshqar/DSCLRCN-PyTorch","reach":null}],"summary":{"unverified":1},"by_repo_kind":{"listed":{"samples":1,"ran":0,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":1,"samples":[{"code_sha256_prefix":"d0608847e36f7ac8","entry":"get_SALICON_subset","repo":"AAshqar/DSCLRCN-PyTorch","repo_kind":"listed","path":"util/data_utils.py","file_url":"https://github.com/AAshqar/DSCLRCN-PyTorch/blob/HEAD/util/data_utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"d0608847e36f7ac8"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}