{"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/panoramic-vision-transformer-for-saliency","title":"Panoramic Vision Transformer for Saliency Detection in 360° Videos","arxiv_id":"2209.08956","date":"2022-09-19","proceeding":null,"authors":["Heeseung Yun","Sehun Lee","Gunhee Kim"],"abstract":"360$^\\circ$ video saliency detection is one of the challenging benchmarks for 360$^\\circ$ video understanding since non-negligible distortion and discontinuity occur in the projection of any format of 360$^\\circ$ videos, and capture-worthy viewpoint in the omnidirectional sphere is ambiguous by nature. We present a new framework named Panoramic Vision Transformer (PAVER). We design the encoder using Vision Transformer with deformable convolution, which enables us not only to plug pretrained models from normal videos into our architecture without additional modules or finetuning but also to perform geometric approximation only once, unlike previous deep CNN-based approaches. Thanks to its powerful encoder, PAVER can learn the saliency from three simple relative relations among local patch features, outperforming state-of-the-art models for the Wild360 benchmark by large margins without supervision or auxiliary information like class activation. We demonstrate the utility of our saliency prediction model with the omnidirectional video quality assessment task in VQA-ODV, where we consistently improve performance without any form of supervision, including head movement.","url_abs":"https://arxiv.org/abs/2209.08956v1","url_pdf":"https://arxiv.org/pdf/2209.08956v1.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":"panoramic-vision-transformer-for-saliency","repo_url":"https://github.com/hs-yn/paver","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"saliency-detection","task_name":"Saliency Detection"},{"task_slug":"saliency-prediction","task_name":"Saliency Prediction"},{"task_slug":"video-quality-assessment","task_name":"Video Quality Assessment"},{"task_slug":"video-saliency-detection","task_name":"Video Saliency Detection"},{"task_slug":"video-understanding","task_name":"Video Understanding"},{"task_slug":"visual-question-answering","task_name":"Visual Question Answering (VQA)"}],"methods":[{"method_slug":"absolute-position-encodings","method_name":"Absolute Position Encodings"},{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"label-smoothing","method_name":"Label Smoothing"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"position-wise-feed-forward-layer","method_name":"Position-Wise Feed-Forward Layer"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"transformer","method_name":"Transformer"},{"method_slug":"vision-transformer","method_name":"Vision Transformer"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2209.08956","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2209.08956"}},"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/hs-yn/paver","reach":null}],"summary":{"ran":3,"ran_draft_wrong":1,"ran_violates":1,"unverified":2},"by_repo_kind":{"official":{"samples":7,"ran":5,"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":0,"samples":[{"code_sha256_prefix":"cc958048d557e1e9","entry":"Attention","repo":"hs-yn/paver","repo_kind":"official","path":"code/model/decoder.py","file_url":"https://github.com/hs-yn/paver/blob/HEAD/code/model/decoder.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"cc958048d557e1e9"}},{"code_sha256_prefix":"ac7ba009078385e6","entry":"Block","repo":"hs-yn/paver","repo_kind":"official","path":"code/model/decoder.py","file_url":"https://github.com/hs-yn/paver/blob/HEAD/code/model/decoder.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"ac7ba009078385e6"}},{"code_sha256_prefix":"511f72cb4c20504a","entry":"DropPath","repo":"hs-yn/paver","repo_kind":"official","path":"code/model/decoder.py","file_url":"https://github.com/hs-yn/paver/blob/HEAD/code/model/decoder.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"511f72cb4c20504a"}},{"code_sha256_prefix":"749238c52b987779","entry":"full_model","repo":"hs-yn/paver","repo_kind":"official","path":"code/model/decoder.py","file_url":"https://github.com/hs-yn/paver/blob/HEAD/code/model/decoder.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"749238c52b987779"}},{"code_sha256_prefix":"49d32e2b965eb4a6","entry":"sphere_to_threed","repo":"hs-yn/paver","repo_kind":"official","path":"code/model/decoder.py","file_url":"https://github.com/hs-yn/paver/blob/HEAD/code/model/decoder.py","link_basis":"first_harvest_node","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"49d32e2b965eb4a6"}},{"code_sha256_prefix":"4268375daf6321ec","entry":"BaseDecoder","repo":"hs-yn/paver","repo_kind":"official","path":"code/model/decoder.py","file_url":"https://github.com/hs-yn/paver/blob/HEAD/code/model/decoder.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"4268375daf6321ec"}},{"code_sha256_prefix":"963c1ed89e281395","entry":"PAVER","repo":"hs-yn/paver","repo_kind":"official","path":"code/model/decoder.py","file_url":"https://github.com/hs-yn/paver/blob/HEAD/code/model/decoder.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"963c1ed89e281395"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}