{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/deep-set-conditioned-latent-representations-1","title":"Deep set conditioned latent representations for action recognition","arxiv_id":"2212.11030","date":"2022-12-21","proceeding":"International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications 2022 2","authors":["Akash Singh","Tom De Schepper","Kevin Mets","Peter Hellinckx","Jose Oramas","Steven Latre"],"abstract":"In recent years multi-label, multi-class video action recognition has gained significant popularity. While reasoning over temporally connected atomic actions is mundane for intelligent species, standard artificial neural networks (ANN) still struggle to classify them. In the real world, atomic actions often temporally connect to form more complex composite actions. The challenge lies in recognising composite action of varying durations while other distinct composite or atomic actions occur in the background. Drawing upon the success of relational networks, we propose methods that learn to reason over the semantic concept of objects and actions. We empirically show how ANNs benefit from pretraining, relational inductive biases and unordered set-based latent representations. In this paper we propose deep set conditioned I3D (SCI3D), a two stream relational network that employs latent representation of state and visual representation for reasoning over events and actions. They learn to reason about temporally connected actions in order to identify all of them in the video. The proposed method achieves an improvement of around 1.49% mAP in atomic action recognition and 17.57% mAP in composite action recognition, over a I3D-NL baseline, on the CATER dataset.","url_abs":"https://arxiv.org/abs/2212.11030v1","url_pdf":"https://arxiv.org/pdf/2212.11030v1.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":[],"tasks":[{"task_slug":"action-recognition-in-videos","task_name":"Action Recognition"},{"task_slug":"atomic-action-recognition","task_name":"Atomic action recognition"},{"task_slug":"composite-action-recognition","task_name":"Composite action recognition"},{"task_slug":"action-recognition","task_name":"Temporal Action Localization"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/atomic-action-recognition-on-cater","task":"Atomic action recognition","dataset":"CATER","model":"SCI3D","rank_in_archive_order":1,"of":4,"metrics":{"Average-mAP":"96.77"},"uses_additional_data":true},{"leaderboard":"/sota/atomic-action-recognition-on-cater","task":"Atomic action recognition","dataset":"CATER","model":"R3D-NL","rank_in_archive_order":2,"of":4,"metrics":{"Average-mAP":"95.28"},"uses_additional_data":false},{"leaderboard":"/sota/atomic-action-recognition-on-cater","task":"Atomic action recognition","dataset":"CATER","model":"Single stream SCI3D","rank_in_archive_order":3,"of":4,"metrics":{"Average-mAP":"91.82"},"uses_additional_data":true},{"leaderboard":"/sota/atomic-action-recognition-on-cater","task":"Atomic action recognition","dataset":"CATER","model":"FasterRCNN","rank_in_archive_order":4,"of":4,"metrics":{"Average-mAP":"63.85"},"uses_additional_data":true},{"leaderboard":"/sota/composite-action-recognition-on-cater","task":"Composite action recognition","dataset":"CATER","model":"Single stream SCI3D","rank_in_archive_order":1,"of":4,"metrics":{"Average-mAP":"69.76"},"uses_additional_data":true},{"leaderboard":"/sota/composite-action-recognition-on-cater","task":"Composite action recognition","dataset":"CATER","model":"SCI3D","rank_in_archive_order":2,"of":4,"metrics":{"Average-mAP":"66.71"},"uses_additional_data":true},{"leaderboard":"/sota/composite-action-recognition-on-cater","task":"Composite action recognition","dataset":"CATER","model":"R3D-NL","rank_in_archive_order":3,"of":4,"metrics":{"Average-mAP":"52.19"},"uses_additional_data":true},{"leaderboard":"/sota/composite-action-recognition-on-cater","task":"Composite action recognition","dataset":"CATER","model":"FasterRCNN","rank_in_archive_order":4,"of":4,"metrics":{"Average-mAP":"25.45"},"uses_additional_data":true}],"syntology":{"syntology_url":"https://syntology.ai/paper/2212.11030","atlas_url":"https://app.syntology.ai/?focus=2212.11030","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"2212.11030"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2212.11030\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2212.11030"},"call":"get_concepts_for_paper(arxiv_id=\"2212.11030\")"}],"by_repo":[],"by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":"the archive holds no code link for this paper","arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"468f6a35dfe2284da580e7e4529f85c87d71b62bb670d938e1fb0aea5c65d524","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}