{"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/oat-object-level-attention-transformer-for","title":"OAT: Object-Level Attention Transformer for Gaze Scanpath Prediction","arxiv_id":"2407.13335","date":"2024-07-18","proceeding":null,"authors":["Yini Fang","Jingling Yu","Haozheng Zhang","Ralf van der Lans","Bertram Shi"],"abstract":"Visual search is important in our daily life. The efficient allocation of visual attention is critical to effectively complete visual search tasks. Prior research has predominantly modelled the spatial allocation of visual attention in images at the pixel level, e.g. using a saliency map. However, emerging evidence shows that visual attention is guided by objects rather than pixel intensities. This paper introduces the Object-level Attention Transformer (OAT), which predicts human scanpaths as they search for a target object within a cluttered scene of distractors. OAT uses an encoder-decoder architecture. The encoder captures information about the position and appearance of the objects within an image and about the target. The decoder predicts the gaze scanpath as a sequence of object fixations, by integrating output features from both the encoder and decoder. We also propose a new positional encoding that better reflects spatial relationships between objects. We evaluated OAT on the Amazon book cover dataset and a new dataset for visual search that we collected. OAT's predicted gaze scanpaths align more closely with human gaze patterns, compared to predictions by algorithms based on spatial attention on both established metrics and a novel behavioural-based metric. Our results demonstrate the generalization ability of OAT, as it accurately predicts human scanpaths for unseen layouts and target objects.","url_abs":"https://arxiv.org/abs/2407.13335v1","url_pdf":"https://arxiv.org/pdf/2407.13335v1.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":"oat-object-level-attention-transformer-for","repo_url":"https://github.com/hkust-nisl/oat_eccv24","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"decoder","task_name":"Decoder"},{"task_slug":"object","task_name":"Object"},{"task_slug":"prediction","task_name":"Prediction"},{"task_slug":"scanpath-prediction","task_name":"Scanpath prediction"}],"methods":[{"method_slug":"align","method_name":"ALIGN"},{"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"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2407.13335","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.13335"}},"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/hkust-nisl/oat_eccv24","reach":{"status":"ok"}}],"summary":{"ran":14,"ran_honours":1,"unverified":3},"by_repo_kind":{"official":{"samples":18,"ran":15,"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":18,"samples":[{"code_sha256_prefix":"f495c083c4b62415","entry":"calcangle","repo":"hkust-nisl/oat_eccv24","repo_kind":"official","path":"src/evaluation/multimatch.py","file_url":"https://github.com/hkust-nisl/oat_eccv24/blob/HEAD/src/evaluation/multimatch.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"f495c083c4b62415"}},{"code_sha256_prefix":"583e0bc15a6d0763","entry":"cart2pol","repo":"hkust-nisl/oat_eccv24","repo_kind":"official","path":"src/evaluation/multimatch.py","file_url":"https://github.com/hkust-nisl/oat_eccv24/blob/HEAD/src/evaluation/multimatch.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"583e0bc15a6d0763"}},{"code_sha256_prefix":"22b9eb9c9b3b5796","entry":"create_mask","repo":"hkust-nisl/oat_eccv24","repo_kind":"official","path":"src/model/models.py","file_url":"https://github.com/hkust-nisl/oat_eccv24/blob/HEAD/src/model/models.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"22b9eb9c9b3b5796"}},{"code_sha256_prefix":"3ee8f4b0078c65d0","entry":"generate_square_subsequent_mask","repo":"hkust-nisl/oat_eccv24","repo_kind":"official","path":"src/model/models.py","file_url":"https://github.com/hkust-nisl/oat_eccv24/blob/HEAD/src/model/models.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"3ee8f4b0078c65d0"}},{"code_sha256_prefix":"2a4597174add2d99","entry":"getFourierPositional","repo":"hkust-nisl/oat_eccv24","repo_kind":"official","path":"src/model/positionalEncoding.py","file_url":"https://github.com/hkust-nisl/oat_eccv24/blob/HEAD/src/model/positionalEncoding.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"2a4597174add2d99"}},{"code_sha256_prefix":"17fa0f31e5bcdb5b","entry":"getSinPositional","repo":"hkust-nisl/oat_eccv24","repo_kind":"official","path":"src/model/positionalEncoding.py","file_url":"https://github.com/hkust-nisl/oat_eccv24/blob/HEAD/src/model/positionalEncoding.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"17fa0f31e5bcdb5b"}},{"code_sha256_prefix":"33805df68cb6892e","entry":"get_emb","repo":"hkust-nisl/oat_eccv24","repo_kind":"official","path":"src/model/positionalEncoding.py","file_url":"https://github.com/hkust-nisl/oat_eccv24/blob/HEAD/src/model/positionalEncoding.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"33805df68cb6892e"}},{"code_sha256_prefix":"46ab31276efa17b5","entry":"get_val_and_tst","repo":"hkust-nisl/oat_eccv24","repo_kind":"official","path":"src/dataBuilders/data_builder.py","file_url":"https://github.com/hkust-nisl/oat_eccv24/blob/HEAD/src/dataBuilders/data_builder.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"46ab31276efa17b5"}},{"code_sha256_prefix":"8a28b6f89b07e4f3","entry":"idx2pos","repo":"hkust-nisl/oat_eccv24","repo_kind":"official","path":"src/evaluation/multimatch.py","file_url":"https://github.com/hkust-nisl/oat_eccv24/blob/HEAD/src/evaluation/multimatch.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"8a28b6f89b07e4f3"}},{"code_sha256_prefix":"729778f138c9b280","entry":"mag","repo":"hkust-nisl/oat_eccv24","repo_kind":"official","path":"src/model/models.py","file_url":"https://github.com/hkust-nisl/oat_eccv24/blob/HEAD/src/model/models.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"729778f138c9b280"}},{"code_sha256_prefix":"039e9f0f0dfbfaca","entry":"match_hist","repo":"hkust-nisl/oat_eccv24","repo_kind":"official","path":"src/evaluation/saliency_metric.py","file_url":"https://github.com/hkust-nisl/oat_eccv24/blob/HEAD/src/evaluation/saliency_metric.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"039e9f0f0dfbfaca"}},{"code_sha256_prefix":"d3d86d1943c5ac37","entry":"normalize","repo":"hkust-nisl/oat_eccv24","repo_kind":"official","path":"src/evaluation/saliency_metric.py","file_url":"https://github.com/hkust-nisl/oat_eccv24/blob/HEAD/src/evaluation/saliency_metric.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"d3d86d1943c5ac37"}},{"code_sha256_prefix":"4bf07207295baa34","entry":"randsplit","repo":"hkust-nisl/oat_eccv24","repo_kind":"official","path":"src/dataBuilders/data_builder.py","file_url":"https://github.com/hkust-nisl/oat_eccv24/blob/HEAD/src/dataBuilders/data_builder.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"4bf07207295baa34"}},{"code_sha256_prefix":"f23c64e951a4b922","entry":"randsplit_comb","repo":"hkust-nisl/oat_eccv24","repo_kind":"official","path":"src/dataBuilders/data_builder.py","file_url":"https://github.com/hkust-nisl/oat_eccv24/blob/HEAD/src/dataBuilders/data_builder.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"f23c64e951a4b922"}},{"code_sha256_prefix":"daf4a2dd832dabd7","entry":"saliency_map_metric","repo":"hkust-nisl/oat_eccv24","repo_kind":"official","path":"src/evaluation/saliency_metric.py","file_url":"https://github.com/hkust-nisl/oat_eccv24/blob/HEAD/src/evaluation/saliency_metric.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"daf4a2dd832dabd7"}},{"code_sha256_prefix":"811a6f146581043b","entry":"getCosSim","repo":"hkust-nisl/oat_eccv24","repo_kind":"official","path":"src/model/positionalEncodingLearned.py","file_url":"https://github.com/hkust-nisl/oat_eccv24/blob/HEAD/src/model/positionalEncodingLearned.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":"811a6f146581043b"}},{"code_sha256_prefix":"3ad8ebeb3af55198","entry":"getEnc","repo":"hkust-nisl/oat_eccv24","repo_kind":"official","path":"src/model/positionalEncodingLearned.py","file_url":"https://github.com/hkust-nisl/oat_eccv24/blob/HEAD/src/model/positionalEncodingLearned.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":"3ad8ebeb3af55198"}},{"code_sha256_prefix":"a46671905c186496","entry":"loss_function","repo":"hkust-nisl/oat_eccv24","repo_kind":"official","path":"src/model/positionalEncodingLearned.py","file_url":"https://github.com/hkust-nisl/oat_eccv24/blob/HEAD/src/model/positionalEncodingLearned.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":"a46671905c186496"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}