{"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/trafficqa-a-question-answering-benchmark-and","title":"SUTD-TrafficQA: A Question Answering Benchmark and an Efficient Network for Video Reasoning over Traffic Events","arxiv_id":"2103.15538","date":"2021-03-29","proceeding":"CVPR 2021 1","authors":["Li Xu","He Huang","Jun Liu"],"abstract":"Traffic event cognition and reasoning in videos is an important task that has a wide range of applications in intelligent transportation, assisted driving, and autonomous vehicles. In this paper, we create a novel dataset, SUTD-TrafficQA (Traffic Question Answering), which takes the form of video QA based on the collected 10,080 in-the-wild videos and annotated 62,535 QA pairs, for benchmarking the cognitive capability of causal inference and event understanding models in complex traffic scenarios. Specifically, we propose 6 challenging reasoning tasks corresponding to various traffic scenarios, so as to evaluate the reasoning capability over different kinds of complex yet practical traffic events. Moreover, we propose Eclipse, a novel Efficient glimpse network via dynamic inference, in order to achieve computation-efficient and reliable video reasoning. The experiments show that our method achieves superior performance while reducing the computation cost significantly. The project page: https://github.com/SUTDCV/SUTD-TrafficQA.","url_abs":"https://arxiv.org/abs/2103.15538v3","url_pdf":"https://arxiv.org/pdf/2103.15538v3.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":"trafficqa-a-question-answering-benchmark-and","repo_url":"https://github.com/SUTDCV/SUTD-TrafficQA","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"trafficqa-a-question-answering-benchmark-and","repo_url":"https://github.com/MarkHershey/arxiv-dl","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"trafficqa-a-question-answering-benchmark-and","repo_url":"https://github.com/saccharomycetes/text-based-traffic-understanding","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"autonomous-vehicles","task_name":"Autonomous Vehicles"},{"task_slug":"benchmarking","task_name":"Benchmarking"},{"task_slug":"causal-inference","task_name":"Causal Inference"},{"task_slug":"question-answering","task_name":"Question Answering"},{"task_slug":"video-question-answering","task_name":"Video Question Answering"},{"task_slug":"visual-question-answering","task_name":"Visual Question Answering (VQA)"}],"methods":[{"method_slug":"causal-inference","method_name":"Causal inference"}],"datasets_introduced":[{"slug":"trafficqa","name":"SUTD-TrafficQA","full_name":""}],"methods_introduced":[],"results":[{"leaderboard":"/sota/video-question-answering-on-sutd-trafficqa","task":"Video Question Answering","dataset":"SUTD-TrafficQA","model":"Eclipse","rank_in_archive_order":3,"of":6,"metrics":{"1/2":"64.77","1/4":"37.05"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2103.15538","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.15538"}},"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/MarkHershey/arxiv-dl","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/saccharomycetes/text-based-traffic-understanding","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/SUTDCV/SUTD-TrafficQA","reach":{"status":"ok"}}],"summary":{"ran":1,"unverified":8},"by_repo_kind":{"listed":{"samples":9,"ran":1,"repositories":2}},"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":2,"samples":[{"code_sha256_prefix":"f2a7b73a8edfbba6","entry":"MyDataset","repo":"saccharomycetes/text-based-traffic-understanding","repo_kind":"listed","path":"code/kg_eval.py","file_url":"https://github.com/saccharomycetes/text-based-traffic-understanding/blob/HEAD/code/kg_eval.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"f2a7b73a8edfbba6"}},{"code_sha256_prefix":"c52680018836e274","entry":"bytes_to_mb","repo":"MarkHershey/arxiv-dl","repo_kind":"listed","path":"src/arxiv_dl/dl_utils.py","file_url":"https://github.com/MarkHershey/arxiv-dl/blob/HEAD/src/arxiv_dl/dl_utils.py","link_basis":"harvester_set","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":"c52680018836e274"}},{"code_sha256_prefix":"5f5f9fd780fd7de2","entry":"bytes_to_mb_str","repo":"MarkHershey/arxiv-dl","repo_kind":"listed","path":"src/arxiv_dl/dl_utils.py","file_url":"https://github.com/MarkHershey/arxiv-dl/blob/HEAD/src/arxiv_dl/dl_utils.py","link_basis":"harvester_set","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":"5f5f9fd780fd7de2"}},{"code_sha256_prefix":"5409824abd030e72","entry":"download_paper","repo":"MarkHershey/arxiv-dl","repo_kind":"listed","path":"src/arxiv_dl/__main__.py","file_url":"https://github.com/MarkHershey/arxiv-dl/blob/HEAD/src/arxiv_dl/__main__.py","link_basis":"harvester_set","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":"5409824abd030e72"}},{"code_sha256_prefix":"ed2cd9478b7e5964","entry":"filename_from_url","repo":"MarkHershey/arxiv-dl","repo_kind":"listed","path":"src/arxiv_dl/dl_utils.py","file_url":"https://github.com/MarkHershey/arxiv-dl/blob/HEAD/src/arxiv_dl/dl_utils.py","link_basis":"harvester_set","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":"ed2cd9478b7e5964"}},{"code_sha256_prefix":"c42544b64dd4e070","entry":"http_download","repo":"MarkHershey/arxiv-dl","repo_kind":"listed","path":"src/arxiv_dl/helpers.py","file_url":"https://github.com/MarkHershey/arxiv-dl/blob/HEAD/src/arxiv_dl/helpers.py","link_basis":"harvester_set","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":"c42544b64dd4e070"}},{"code_sha256_prefix":"2068451b9dddb6b3","entry":"normalize_paper_title","repo":"MarkHershey/arxiv-dl","repo_kind":"listed","path":"src/arxiv_dl/helpers.py","file_url":"https://github.com/MarkHershey/arxiv-dl/blob/HEAD/src/arxiv_dl/helpers.py","link_basis":"harvester_set","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":"2068451b9dddb6b3"}},{"code_sha256_prefix":"b827f2f33d8c9d54","entry":"t5_eval","repo":"saccharomycetes/text-based-traffic-understanding","repo_kind":"listed","path":"code/kg_eval.py","file_url":"https://github.com/saccharomycetes/text-based-traffic-understanding/blob/HEAD/code/kg_eval.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"b827f2f33d8c9d54"}},{"code_sha256_prefix":"3bebc05a8d967b01","entry":"valid_arxiv_id","repo":"MarkHershey/arxiv-dl","repo_kind":"listed","path":"src/arxiv_dl/target_parser.py","file_url":"https://github.com/MarkHershey/arxiv-dl/blob/HEAD/src/arxiv_dl/target_parser.py","link_basis":"harvester_set","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":"3bebc05a8d967b01"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}