{"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":"/task/video-classification/papers/2","list_of":"/task/video-classification","task":"Video Classification","archive":{"snapshot":"2025-07-28"},"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"archive","order_definition":"repositories listed in the archive (most first), then date (newest first), then slug","page":2,"pages_in_order":5,"rows_per_page":100,"rows":[101,200],"of":455,"counts":{"archive_papers_tagged":455,"with_a_code_link":206,"where_syntology_ran_a_sample":50,"not_listed_spam_title":0,"listed":455,"listed_where_code_ran":50,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":40,"every_run_a_failure_of_syntologys_instrument":10,"listed_with_a_run_with_no_instrument_failure":40,"listed_every_run_a_failure_of_syntologys_instrument":10,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"first_page":"/task/video-classification","prev":"/task/video-classification","next":"/task/video-classification/papers/3","papers":[{"url":"/paper/self-vs-self-supervised-encoding-learning-for","slug":"self-vs-self-supervised-encoding-learning-for","title":"SELF-VS: Self-supervised Encoding Learning For Video Summarization","date":"2023-03-28","arxiv_id":"2303.15993","repositories_listed":1,"syntology":null},{"url":"/paper/the-effectiveness-of-mae-pre-pretraining-for","slug":"the-effectiveness-of-mae-pre-pretraining-for","title":"The effectiveness of MAE pre-pretraining for billion-scale pretraining","date":"2023-03-23","arxiv_id":"2303.13496","repositories_listed":1,"syntology":null},{"url":"/paper/musclemap-towards-video-based-activated","slug":"musclemap-towards-video-based-activated","title":"Towards Activated Muscle Group Estimation in the Wild","date":"2023-03-02","arxiv_id":"2303.00952","repositories_listed":1,"syntology":null},{"url":"/paper/augmenting-ego-vehicle-for-traffic-near-miss","slug":"augmenting-ego-vehicle-for-traffic-near-miss","title":"Augmenting Ego-Vehicle for Traffic Near-Miss and Accident Classification Dataset using Manipulating Conditional Style Translation","date":"2023-01-06","arxiv_id":"2301.02726","repositories_listed":1,"syntology":null},{"url":"/paper/efficient-movie-scene-detection-using-state","slug":"efficient-movie-scene-detection-using-state","title":"Efficient Movie Scene Detection using State-Space Transformers","date":"2022-12-29","arxiv_id":"2212.14427","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/efficient-movie-scene-detection-using-state#ran","syntology_url":"https://syntology.ai/paper/2212.14427","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2212.14427"}},"official":{"repos":["md-mohaiminul/trans4mer"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/evaluation-of-fem-and-mlfem-ai-explainers-in","slug":"evaluation-of-fem-and-mlfem-ai-explainers-in","title":"Evaluation of Explanation Methods of AI -- CNNs in Image Classification Tasks with Reference-based and No-reference Metrics","date":"2022-12-02","arxiv_id":"2212.01222","repositories_listed":1,"syntology":null},{"url":"/paper/a-unified-multimodal-de-and-re-coupling","slug":"a-unified-multimodal-de-and-re-coupling","title":"A Unified Multimodal De- and Re-coupling Framework for RGB-D Motion Recognition","date":"2022-11-16","arxiv_id":"2211.09146","repositories_listed":1,"syntology":null},{"url":"/paper/overlooked-video-classification-in-weakly","slug":"overlooked-video-classification-in-weakly","title":"Overlooked Video Classification in Weakly Supervised Video Anomaly Detection","date":"2022-10-13","arxiv_id":"2210.06688","repositories_listed":1,"syntology":null},{"url":"/paper/s4nd-modeling-images-and-videos-as","slug":"s4nd-modeling-images-and-videos-as","title":"S4ND: Modeling Images and Videos as Multidimensional Signals Using State Spaces","date":"2022-10-12","arxiv_id":"2210.06583","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/s4nd-modeling-images-and-videos-as#ran","syntology_url":"https://syntology.ai/paper/2210.06583","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.06583"}},"official":{"repos":["hazyresearch/state-spaces"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["community"]}}},{"url":"/paper/towards-smart-city-security-violence-and","slug":"towards-smart-city-security-violence-and","title":"SSIVD-Net: A Novel Salient Super Image Classification & Detection Technique for Weaponized Violence","date":"2022-07-26","arxiv_id":"2207.12850","repositories_listed":1,"syntology":null},{"url":"/paper/visually-explaining-3d-cnn-predictions-for","slug":"visually-explaining-3d-cnn-predictions-for","title":"Adaptive occlusion sensitivity analysis for visually explaining video recognition networks","date":"2022-07-26","arxiv_id":"2207.12859","repositories_listed":1,"syntology":null},{"url":"/paper/exploring-fine-grained-audiovisual","slug":"exploring-fine-grained-audiovisual","title":"Exploring Fine-Grained Audiovisual Categorization with the SSW60 Dataset","date":"2022-07-21","arxiv_id":"2207.10664","repositories_listed":1,"syntology":null},{"url":"/paper/inductive-and-transductive-few-shot-video","slug":"inductive-and-transductive-few-shot-video","title":"Inductive and Transductive Few-Shot Video Classification via Appearance and Temporal Alignments","date":"2022-07-21","arxiv_id":"2207.10785","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":1,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result","sample_list":"/paper/inductive-and-transductive-few-shot-video#ran","syntology_url":"https://syntology.ai/paper/2207.10785","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2207.10785"}},"official":{"repos":["vinairesearch/fsvc-ata"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/goca-guided-online-cluster-assignment-for","slug":"goca-guided-online-cluster-assignment-for","title":"GOCA: Guided Online Cluster Assignment for Self-Supervised Video Representation Learning","date":"2022-07-20","arxiv_id":"2207.10158","repositories_listed":1,"syntology":null},{"url":"/paper/long-term-leap-attention-short-term-periodic","slug":"long-term-leap-attention-short-term-periodic","title":"Long-term Leap Attention, Short-term Periodic Shift for Video Classification","date":"2022-07-12","arxiv_id":"2207.05526","repositories_listed":1,"syntology":null},{"url":"/paper/key-frame-guided-network-for-thyroid-nodule","slug":"key-frame-guided-network-for-thyroid-nodule","title":"Key-frame Guided Network for Thyroid Nodule Recognition using Ultrasound Videos","date":"2022-06-27","arxiv_id":"2206.13318","repositories_listed":1,"syntology":null},{"url":"/paper/analysis-and-extensions-of-adversarial","slug":"analysis-and-extensions-of-adversarial","title":"Analysis and Extensions of Adversarial Training for Video Classification","date":"2022-06-16","arxiv_id":"2206.07953","repositories_listed":1,"syntology":null},{"url":"/paper/uni-perceiver-moe-learning-sparse-generalist","slug":"uni-perceiver-moe-learning-sparse-generalist","title":"Uni-Perceiver-MoE: Learning Sparse Generalist Models with Conditional MoEs","date":"2022-06-09","arxiv_id":"2206.04674","repositories_listed":1,"syntology":null},{"url":"/paper/convex-combination-consistency-between","slug":"convex-combination-consistency-between","title":"Convex Combination Consistency between Neighbors for Weakly-supervised Action Localization","date":"2022-05-01","arxiv_id":"2205.00400","repositories_listed":1,"syntology":null},{"url":"/paper/vpai-lab-at-medvidqa-2022-a-two-stage-cross","slug":"vpai-lab-at-medvidqa-2022-a-two-stage-cross","title":"VPAI_Lab at MedVidQA 2022: A Two-Stage Cross-modal Fusion Method for Medical Instructional Video Classification","date":"2022-05-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/attention-in-attention-modeling-context","slug":"attention-in-attention-modeling-context","title":"Attention in Attention: Modeling Context Correlation for Efficient Video Classification","date":"2022-04-20","arxiv_id":"2204.09303","repositories_listed":1,"syntology":null},{"url":"/paper/long-movie-clip-classification-with-state","slug":"long-movie-clip-classification-with-state","title":"Long Movie Clip Classification with State-Space Video Models","date":"2022-04-04","arxiv_id":"2204.01692","repositories_listed":1,"syntology":{"n":18,"n_ran":11,"n_constructed":2,"n_ran_checked":3,"n_instrument":8,"n_unverified":7,"n_honours":1,"n_violates":0,"n_no_contract":2,"n_pointer_only":2,"phrase":"11 ran (of which 2 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 8 where Syntology's instrument failed) · 7 unverified","sample_list":"/paper/long-movie-clip-classification-with-state#ran","syntology_url":"https://syntology.ai/paper/2204.01692","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2204.01692"}},"official":{"repos":["md-mohaiminul/ViS4mer"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":2,"n_ran_no_instrument_failure":3,"n_unverified":7,"ran_from_kinds":["official","unlocated"]}}},{"url":"/paper/stylefool-fooling-video-classification","slug":"stylefool-fooling-video-classification","title":"StyleFool: Fooling Video Classification Systems via Style Transfer","date":"2022-03-30","arxiv_id":"2203.16000","repositories_listed":1,"syntology":null},{"url":"/paper/alignment-uniformity-aware-representation","slug":"alignment-uniformity-aware-representation","title":"Alignment-Uniformity aware Representation Learning for Zero-shot Video Classification","date":"2022-03-29","arxiv_id":"2203.15381","repositories_listed":1,"syntology":{"n":5,"n_ran":2,"n_constructed":1,"n_ran_checked":1,"n_instrument":1,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":5,"phrase":"2 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/alignment-uniformity-aware-representation#ran","syntology_url":"https://syntology.ai/paper/2203.15381","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.15381"}},"official":{"repos":["ShipuLoveMili/CVPR2022-AURL"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/unsupervised-pre-training-for-temporal-action","slug":"unsupervised-pre-training-for-temporal-action","title":"Unsupervised Pre-training for Temporal Action Localization Tasks","date":"2022-03-25","arxiv_id":"2203.13609","repositories_listed":1,"syntology":null},{"url":"/paper/effectively-leveraging-multi-modal-features","slug":"effectively-leveraging-multi-modal-features","title":"Movie Genre Classification by Language Augmentation and Shot Sampling","date":"2022-03-24","arxiv_id":"2203.13281","repositories_listed":1,"syntology":null},{"url":"/paper/learning-to-recognize-procedural-activities","slug":"learning-to-recognize-procedural-activities","title":"Learning To Recognize Procedural Activities with Distant Supervision","date":"2022-01-26","arxiv_id":"2201.10990","repositories_listed":1,"syntology":null},{"url":"/paper/capturing-temporal-information-in-a-single","slug":"capturing-temporal-information-in-a-single","title":"Capturing Temporal Information in a Single Frame: Channel Sampling Strategies for Action Recognition","date":"2022-01-25","arxiv_id":"2201.10394","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":3,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 3 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/capturing-temporal-information-in-a-single#ran","syntology_url":"https://syntology.ai/paper/2201.10394","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2201.10394"}},"official":{"repos":["kiyoon/channel_sampling"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/approaches-toward-physical-and-general-video","slug":"approaches-toward-physical-and-general-video","title":"Approaches Toward Physical and General Video Anomaly Detection","date":"2021-12-14","arxiv_id":"2112.07661","repositories_listed":1,"syntology":null},{"url":"/paper/staf-a-spatio-temporal-attention-fusion","slug":"staf-a-spatio-temporal-attention-fusion","title":"MASTAF: A Model-Agnostic Spatio-Temporal Attention Fusion Network for Few-shot Video Classification","date":"2021-12-08","arxiv_id":"2112.04585","repositories_listed":1,"syntology":null},{"url":"/paper/ats-adaptive-token-sampling-for-efficient","slug":"ats-adaptive-token-sampling-for-efficient","title":"Adaptive Token Sampling For Efficient Vision Transformers","date":"2021-11-30","arxiv_id":"2111.15667","repositories_listed":1,"syntology":{"n":5,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":3,"n_pointer_only":5,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/ats-adaptive-token-sampling-for-efficient#ran","syntology_url":"https://syntology.ai/paper/2111.15667","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2111.15667"}},"official":{"repos":["adaptivetokensampling/ATS"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/adapool-exponential-adaptive-pooling-for","slug":"adapool-exponential-adaptive-pooling-for","title":"AdaPool: Exponential Adaptive Pooling for Information-Retaining Downsampling","date":"2021-11-01","arxiv_id":"2111.00772","repositories_listed":1,"syntology":null},{"url":"/paper/metavd-a-meta-video-dataset-for-enhancing","slug":"metavd-a-meta-video-dataset-for-enhancing","title":"MetaVD: A Meta Video Dataset for enhancing human action recognition datasets","date":"2021-11-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/a-closer-look-at-few-shot-video","slug":"a-closer-look-at-few-shot-video","title":"A Closer Look at Few-Shot Video Classification: A New Baseline and Benchmark","date":"2021-10-24","arxiv_id":"2110.12358","repositories_listed":1,"syntology":null},{"url":"/paper/adversarial-attacks-on-black-box-video","slug":"adversarial-attacks-on-black-box-video","title":"Adversarial Attacks on Black Box Video Classifiers: Leveraging the Power of Geometric Transformations","date":"2021-10-05","arxiv_id":"2110.01823","repositories_listed":1,"syntology":{"n":9,"n_ran":6,"n_constructed":0,"n_ran_checked":0,"n_instrument":6,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":9,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 6 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/adversarial-attacks-on-black-box-video#ran","syntology_url":"https://syntology.ai/paper/2110.01823","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.01823"}},"official":{"repos":["sli057/Geo-TRAP"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/a-unified-taxonomy-and-multimodal-dataset-for","slug":"a-unified-taxonomy-and-multimodal-dataset-for","title":"A Unified Taxonomy and Multimodal Dataset for Events in Invasion Games","date":"2021-08-25","arxiv_id":"2108.11149","repositories_listed":1,"syntology":null},{"url":"/paper/attention-bottlenecks-for-multimodal-fusion","slug":"attention-bottlenecks-for-multimodal-fusion","title":"Attention Bottlenecks for Multimodal Fusion","date":"2021-06-30","arxiv_id":"2107.00135","repositories_listed":1,"syntology":null},{"url":"/paper/self-supervised-video-representation-learning-7","slug":"self-supervised-video-representation-learning-7","title":"Self-supervised Video Representation Learning with Cross-Stream Prototypical Contrasting","date":"2021-06-18","arxiv_id":"2106.10137","repositories_listed":1,"syntology":null},{"url":"/paper/ct-net-channel-tensorization-network-for-1","slug":"ct-net-channel-tensorization-network-for-1","title":"CT-Net: Channel Tensorization Network for Video Classification","date":"2021-06-03","arxiv_id":"2106.01603","repositories_listed":1,"syntology":{"n":13,"n_ran":11,"n_constructed":2,"n_ran_checked":4,"n_instrument":7,"n_unverified":2,"n_honours":1,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"11 ran (of which 2 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 7 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/ct-net-channel-tensorization-network-for-1#ran","syntology_url":"https://syntology.ai/paper/2106.01603","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.01603"}},"official":{"repos":["Andy1621/CT-Net"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":2,"n_ran_no_instrument_failure":4,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/a-spatio-temporal-attention-based-model-for-1","slug":"a-spatio-temporal-attention-based-model-for-1","title":"A Spatio-temporal Attention-based Model for Infant Movement Assessment from Videos","date":"2021-05-20","arxiv_id":"2105.09783","repositories_listed":1,"syntology":null},{"url":"/paper/home-action-genome-cooperative-compositional","slug":"home-action-genome-cooperative-compositional","title":"Home Action Genome: Cooperative Compositional Action Understanding","date":"2021-05-11","arxiv_id":"2105.05226","repositories_listed":1,"syntology":{"n":16,"n_ran":13,"n_constructed":0,"n_ran_checked":12,"n_instrument":1,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":12,"n_pointer_only":0,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 0 violated, 12 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/home-action-genome-cooperative-compositional#ran","syntology_url":"https://syntology.ai/paper/2105.05226","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2105.05226"}},"official":{"repos":["nishantrai18/homage"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":12,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/learning-implicit-temporal-alignment-for-few","slug":"learning-implicit-temporal-alignment-for-few","title":"Learning Implicit Temporal Alignment for Few-shot Video Classification","date":"2021-05-11","arxiv_id":"2105.04823","repositories_listed":1,"syntology":null},{"url":"/paper/ranp-resource-aware-neuron-pruning-at-1","slug":"ranp-resource-aware-neuron-pruning-at-1","title":"RANP: Resource Aware Neuron Pruning at Initialization for 3D CNNs","date":"2021-02-09","arxiv_id":"2103.08457","repositories_listed":1,"syntology":null},{"url":"/paper/piano-skills-assessment","slug":"piano-skills-assessment","title":"Piano Skills Assessment","date":"2021-01-13","arxiv_id":"2101.04884","repositories_listed":1,"syntology":null},{"url":"/paper/self-supervised-pretraining-of-3d-features-on","slug":"self-supervised-pretraining-of-3d-features-on","title":"Self-Supervised Pretraining of 3D Features on any Point-Cloud","date":"2021-01-07","arxiv_id":"2101.02691","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/self-supervised-pretraining-of-3d-features-on#ran","syntology_url":"https://syntology.ai/paper/2101.02691","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2101.02691"}},"official":{"repos":["facebookresearch/DepthContrast"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/diverse-temporal-aggregation-and-depthwise","slug":"diverse-temporal-aggregation-and-depthwise","title":"Diverse Temporal Aggregation and Depthwise Spatiotemporal Factorization for Efficient Video Classification","date":"2020-12-01","arxiv_id":"2012.00317","repositories_listed":1,"syntology":null},{"url":"/paper/is-normalization-indispensable-for-training","slug":"is-normalization-indispensable-for-training","title":"Is normalization indispensable for training deep neural network?","date":"2020-12-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/deep-multimodality-learning-for-uav-video","slug":"deep-multimodality-learning-for-uav-video","title":"Deep Multimodality Learning for UAV Video Aesthetic Quality Assessment","date":"2020-11-04","arxiv_id":"2011.02356","repositories_listed":1,"syntology":null},{"url":"/paper/ranp-resource-aware-neuron-pruning-at","slug":"ranp-resource-aware-neuron-pruning-at","title":"RANP: Resource Aware Neuron Pruning at Initialization for 3D CNNs","date":"2020-10-06","arxiv_id":"2010.02488","repositories_listed":1,"syntology":null},{"url":"/paper/dynamic-regions-graph-neural-networks-for","slug":"dynamic-regions-graph-neural-networks-for","title":"Discovering Dynamic Salient Regions for Spatio-Temporal Graph Neural Networks","date":"2020-09-17","arxiv_id":"2009.08427","repositories_listed":1,"syntology":{"n":2,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 2 unverified","sample_list":"/paper/dynamic-regions-graph-neural-networks-for#ran","syntology_url":"https://syntology.ai/paper/2009.08427","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2009.08427"}},"official":{"repos":["bit-ml/dyreg-gnn"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":[]}}},{"url":"/paper/learning-audio-visual-representations-with","slug":"learning-audio-visual-representations-with","title":"Active Contrastive Learning of Audio-Visual Video Representations","date":"2020-08-31","arxiv_id":"2009.09805","repositories_listed":1,"syntology":{"n":10,"n_ran":9,"n_constructed":0,"n_ran_checked":9,"n_instrument":0,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":8,"n_pointer_only":1,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 1 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/learning-audio-visual-representations-with#ran","syntology_url":"https://syntology.ai/paper/2009.09805","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2009.09805"}},"official":{"repos":["yunyikristy/CM-ACC"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/making-a-case-for-3d-convolutions-for-object","slug":"making-a-case-for-3d-convolutions-for-object","title":"Making a Case for 3D Convolutions for Object Segmentation in Videos","date":"2020-08-26","arxiv_id":"2008.11516","repositories_listed":1,"syntology":{"n":9,"n_ran":9,"n_constructed":0,"n_ran_checked":6,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":0,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/making-a-case-for-3d-convolutions-for-object#ran","syntology_url":"https://syntology.ai/paper/2008.11516","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2008.11516"}},"official":{"repos":["sabarim/3DC-Seg"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/actor-action-video-classification-csc-249-449","slug":"actor-action-video-classification-csc-249-449","title":"Actor-Action Video Classification CSC 249/449 Spring 2020 Challenge Report","date":"2020-08-01","arxiv_id":"2008.00141","repositories_listed":1,"syntology":null},{"url":"/paper/approximated-bilinear-modules-for-temporal-1","slug":"approximated-bilinear-modules-for-temporal-1","title":"Approximated Bilinear Modules for Temporal Modeling","date":"2020-07-25","arxiv_id":"2007.12887","repositories_listed":1,"syntology":null},{"url":"/paper/region-based-non-local-operation-for-video","slug":"region-based-non-local-operation-for-video","title":"Region-based Non-local Operation for Video Classification","date":"2020-07-17","arxiv_id":"2007.09033","repositories_listed":1,"syntology":null},{"url":"/paper/generalized-many-way-few-shot-video","slug":"generalized-many-way-few-shot-video","title":"Generalized Few-Shot Video Classification with Video Retrieval and Feature Generation","date":"2020-07-09","arxiv_id":"2007.04755","repositories_listed":1,"syntology":null},{"url":"/paper/nlp-based-feature-extraction-for-the","slug":"nlp-based-feature-extraction-for-the","title":"NLP-based Feature Extraction for the Detection of COVID-19 Misinformation Videos on YouTube","date":"2020-07-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/smallbignet-integrating-core-and-contextual-1","slug":"smallbignet-integrating-core-and-contextual-1","title":"SmallBigNet: Integrating Core and Contextual Views for Video Classification","date":"2020-06-25","arxiv_id":"2006.14582","repositories_listed":1,"syntology":{"n":3,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"0 ran · 3 unverified","sample_list":"/paper/smallbignet-integrating-core-and-contextual-1#ran","syntology_url":"https://syntology.ai/paper/2006.14582","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2006.14582"}},"official":{"repos":["xhl-video/SmallBigNet"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":3,"ran_from_kinds":[]}}},{"url":"/paper/learn-to-cycle-time-consistent-feature","slug":"learn-to-cycle-time-consistent-feature","title":"Learn to cycle: Time-consistent feature discovery for action recognition","date":"2020-06-15","arxiv_id":"2006.08247","repositories_listed":1,"syntology":null},{"url":"/paper/pipenet-selective-modal-pipeline-of-fusion","slug":"pipenet-selective-modal-pipeline-of-fusion","title":"PipeNet: Selective Modal Pipeline of Fusion Network for Multi-Modal Face Anti-Spoofing","date":"2020-04-24","arxiv_id":"2004.11744","repositories_listed":1,"syntology":null},{"url":"/paper/convolutional-spiking-neural-networks-for","slug":"convolutional-spiking-neural-networks-for","title":"Convolutional Spiking Neural Networks for Spatio-Temporal Feature Extraction","date":"2020-03-27","arxiv_id":"2003.12346","repositories_listed":1,"syntology":null},{"url":"/paper/motion-excited-sampler-video-adversarial","slug":"motion-excited-sampler-video-adversarial","title":"Motion-Excited Sampler: Video Adversarial Attack with Sparked Prior","date":"2020-03-17","arxiv_id":"2003.07637","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/motion-excited-sampler-video-adversarial#ran","syntology_url":"https://syntology.ai/paper/2003.07637","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2003.07637"}},"official":{"repos":["xiaofanustc/ME-Sampler"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/rethinking-zero-shot-video-classification-end","slug":"rethinking-zero-shot-video-classification-end","title":"Rethinking Zero-shot Video Classification: End-to-end Training for Realistic Applications","date":"2020-03-03","arxiv_id":"2003.01455","repositories_listed":1,"syntology":{"n":12,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":0,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/rethinking-zero-shot-video-classification-end#ran","syntology_url":"https://syntology.ai/paper/2003.01455","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2003.01455"}},"official":{"repos":["bbrattoli/ZeroShotVideoClassification"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/patternless-adversarial-attacks-on-video","slug":"patternless-adversarial-attacks-on-video","title":"Over-the-Air Adversarial Flickering Attacks against Video Recognition Networks","date":"2020-02-12","arxiv_id":"2002.05123","repositories_listed":1,"syntology":null},{"url":"/paper/stage-spatio-temporal-attention-on-graph","slug":"stage-spatio-temporal-attention-on-graph","title":"Video action detection by learning graph-based spatio-temporal interactions","date":"2019-12-09","arxiv_id":"1912.04316","repositories_listed":1,"syntology":null},{"url":"/paper/adversarial-pyramid-network-for-video-domain","slug":"adversarial-pyramid-network-for-video-domain","title":"VideoDG: Generalizing Temporal Relations in Videos to Novel Domains","date":"2019-12-08","arxiv_id":"1912.03716","repositories_listed":1,"syntology":null},{"url":"/paper/fast-non-local-neural-networks-with-spectral","slug":"fast-non-local-neural-networks-with-spectral","title":"Fast Non-Local Neural Networks with Spectral Residual Learning","date":"2019-10-15","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/loss-switching-fusion-with-similarity-search","slug":"loss-switching-fusion-with-similarity-search","title":"Loss Switching Fusion with Similarity Search for Video Classification","date":"2019-06-27","arxiv_id":"1906.11465","repositories_listed":1,"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"0 ran · 1 unverified","sample_list":"/paper/loss-switching-fusion-with-similarity-search#ran","syntology_url":"https://syntology.ai/paper/1906.11465","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1906.11465"}},"official":{"repos":["LeiWangR/LSFNet"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"url":"/paper/brain-signal-classification-via-learning","slug":"brain-signal-classification-via-learning","title":"EEG-based Emotional Video Classification via Learning Connectivity Structure","date":"2019-05-28","arxiv_id":"1905.11678","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/brain-signal-classification-via-learning#ran","syntology_url":"https://syntology.ai/paper/1905.11678","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1905.11678"}},"official":{"repos":["ELEMKEP/bsc_lcs"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/hallucinating-optical-flow-features-for-video","slug":"hallucinating-optical-flow-features-for-video","title":"Hallucinating Optical Flow Features for Video Classification","date":"2019-05-28","arxiv_id":"1905.11799","repositories_listed":1,"syntology":null},{"url":"/paper/exploring-temporal-information-for-improved","slug":"exploring-temporal-information-for-improved","title":"Exploring Temporal Information for Improved Video Understanding","date":"2019-05-25","arxiv_id":"1905.10654","repositories_listed":1,"syntology":null},{"url":"/paper/budgeted-training-rethinking-deep-neural","slug":"budgeted-training-rethinking-deep-neural","title":"Budgeted Training: Rethinking Deep Neural Network Training Under Resource Constraints","date":"2019-05-12","arxiv_id":"1905.04753","repositories_listed":1,"syntology":null},{"url":"/paper/holistic-large-scale-video-understanding","slug":"holistic-large-scale-video-understanding","title":"Large Scale Holistic Video Understanding","date":"2019-04-25","arxiv_id":"1904.11451","repositories_listed":1,"syntology":null},{"url":"/paper/multi-branch-tensor-network-structure-for","slug":"multi-branch-tensor-network-structure-for","title":"Multi-Branch Tensor Network Structure for Tensor-Train Discriminant Analysis","date":"2019-04-15","arxiv_id":"1904.06788","repositories_listed":1,"syntology":null},{"url":"/paper/self-supervised-spatio-temporal","slug":"self-supervised-spatio-temporal","title":"Self-supervised Spatio-temporal Representation Learning for Videos by Predicting Motion and Appearance Statistics","date":"2019-04-07","arxiv_id":"1904.03597","repositories_listed":1,"syntology":null},{"url":"/paper/robust-real-time-violence-detection-in-video","slug":"robust-real-time-violence-detection-in-video","title":"Robust Real-Time Violence Detection in Video Using CNN And LSTM","date":"2019-03-27","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/video-based-surgical-skill-assessment-using","slug":"video-based-surgical-skill-assessment-using","title":"Video-based surgical skill assessment using 3D convolutional neural networks","date":"2019-03-06","arxiv_id":"1903.02306","repositories_listed":1,"syntology":null},{"url":"/paper/efficient-video-classification-using-fewer","slug":"efficient-video-classification-using-fewer","title":"Efficient Video Classification Using Fewer Frames","date":"2019-02-27","arxiv_id":"1902.10640","repositories_listed":1,"syntology":null},{"url":"/paper/saliency-tubes-visual-explanations-for-spatio","slug":"saliency-tubes-visual-explanations-for-spatio","title":"Saliency Tubes: Visual Explanations for Spatio-Temporal Convolutions","date":"2019-02-04","arxiv_id":"1902.01078","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/saliency-tubes-visual-explanations-for-spatio#ran","syntology_url":"https://syntology.ai/paper/1902.01078","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1902.01078"}},"official":{"repos":["alexandrosstergiou/Saliency-Tubes-Visual-Explanations-for-Spatio-Temporal-Convolutions"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/adversarial-framing-for-image-and-video","slug":"adversarial-framing-for-image-and-video","title":"Adversarial Framing for Image and Video Classification","date":"2018-12-11","arxiv_id":"1812.04599","repositories_listed":1,"syntology":null},{"url":"/paper/deep-rnn-framework-for-visual-sequential","slug":"deep-rnn-framework-for-visual-sequential","title":"Deep RNN Framework for Visual Sequential Applications","date":"2018-11-25","arxiv_id":"1811.09961","repositories_listed":1,"syntology":null},{"url":"/paper/nextvlad-an-efficient-neural-network-to","slug":"nextvlad-an-efficient-neural-network-to","title":"NeXtVLAD: An Efficient Neural Network to Aggregate Frame-level Features for Large-scale Video Classification","date":"2018-11-12","arxiv_id":"1811.05014","repositories_listed":1,"syntology":{"n":7,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/nextvlad-an-efficient-neural-network-to#ran","syntology_url":"https://syntology.ai/paper/1811.05014","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1811.05014"}},"official":null}},{"url":"/paper/training-compact-deep-learning-models-for","slug":"training-compact-deep-learning-models-for","title":"Training compact deep learning models for video classification using circulant matrices","date":"2018-10-02","arxiv_id":"1810.01140","repositories_listed":1,"syntology":null},{"url":"/paper/learnable-pooling-methods-for-video","slug":"learnable-pooling-methods-for-video","title":"Learnable Pooling Methods for Video Classification","date":"2018-10-01","arxiv_id":"1810.00530","repositories_listed":1,"syntology":null},{"url":"/paper/rate-accuracy-trade-off-in-video","slug":"rate-accuracy-trade-off-in-video","title":"Rate-Accuracy Trade-Off In Video Classification With Deep Convolutional Neural Networks","date":"2018-09-27","arxiv_id":"1810.03964","repositories_listed":1,"syntology":null},{"url":"/paper/adversarial-perturbations-against-real-time","slug":"adversarial-perturbations-against-real-time","title":"Adversarial Perturbations Against Real-Time Video Classification Systems","date":"2018-07-02","arxiv_id":"1807.00458","repositories_listed":1,"syntology":null},{"url":"/paper/on-the-effectiveness-of-task-granularity-for","slug":"on-the-effectiveness-of-task-granularity-for","title":"On the effectiveness of task granularity for transfer learning","date":"2018-04-24","arxiv_id":"1804.09235","repositories_listed":1,"syntology":null},{"url":"/paper/mltuner-system-support-for-automatic-machine","slug":"mltuner-system-support-for-automatic-machine","title":"MLtuner: System Support for Automatic Machine Learning Tuning","date":"2018-03-20","arxiv_id":"1803.07445","repositories_listed":1,"syntology":null},{"url":"/paper/structured-label-inference-for-visual","slug":"structured-label-inference-for-visual","title":"Structured Label Inference for Visual Understanding","date":"2018-02-18","arxiv_id":"1802.06459","repositories_listed":1,"syntology":null},{"url":"/paper/appearance-and-relation-networks-for-video","slug":"appearance-and-relation-networks-for-video","title":"Appearance-and-Relation Networks for Video Classification","date":"2017-11-24","arxiv_id":"1711.09125","repositories_listed":1,"syntology":null},{"url":"/paper/uts-submission-to-google-youtube-8m-challenge","slug":"uts-submission-to-google-youtube-8m-challenge","title":"UTS submission to Google YouTube-8M Challenge 2017","date":"2017-07-13","arxiv_id":"1707.04143","repositories_listed":1,"syntology":null},{"url":"/paper/hierarchical-deep-recurrent-architecture-for","slug":"hierarchical-deep-recurrent-architecture-for","title":"Hierarchical Deep Recurrent Architecture for Video Understanding","date":"2017-07-11","arxiv_id":"1707.03296","repositories_listed":1,"syntology":null},{"url":"/paper/tensor-train-recurrent-neural-networks-for","slug":"tensor-train-recurrent-neural-networks-for","title":"Tensor-Train Recurrent Neural Networks for Video Classification","date":"2017-07-06","arxiv_id":"1707.01786","repositories_listed":1,"syntology":null},{"url":"/paper/the-youtube-8m-kaggle-competition-challenges","slug":"the-youtube-8m-kaggle-competition-challenges","title":"The YouTube-8M Kaggle Competition: Challenges and Methods","date":"2017-06-28","arxiv_id":"1706.09274","repositories_listed":1,"syntology":null},{"url":"/paper/encoding-video-and-label-priors-for-multi","slug":"encoding-video-and-label-priors-for-multi","title":"Encoding Video and Label Priors for Multi-label Video Classification on YouTube-8M dataset","date":"2017-06-24","arxiv_id":"1706.07960","repositories_listed":1,"syntology":null},{"url":"/paper/truly-multi-modal-youtube-8m-video","slug":"truly-multi-modal-youtube-8m-video","title":"Truly Multi-modal YouTube-8M Video Classification with Video, Audio, and Text","date":"2017-06-17","arxiv_id":"1706.05461","repositories_listed":1,"syntology":null},{"url":"/paper/the-monkeytyping-solution-to-the-youtube-8m","slug":"the-monkeytyping-solution-to-the-youtube-8m","title":"The Monkeytyping Solution to the YouTube-8M Video Understanding Challenge","date":"2017-06-16","arxiv_id":"1706.05150","repositories_listed":1,"syntology":null},{"url":"/paper/deep-learning-for-video-classification-and","slug":"deep-learning-for-video-classification-and","title":"Deep Learning for Video Classification and Captioning","date":"2016-09-22","arxiv_id":"1609.06782","repositories_listed":1,"syntology":null},{"url":"/paper/analyzing-linear-dynamical-systems-from","slug":"analyzing-linear-dynamical-systems-from","title":"Analyzing Linear Dynamical Systems: From Modeling to Coding and Learning","date":"2016-08-03","arxiv_id":"1608.01059","repositories_listed":1,"syntology":null},{"url":"/paper/cuhk-ethz-siat-submission-to-activitynet","slug":"cuhk-ethz-siat-submission-to-activitynet","title":"CUHK & ETHZ & SIAT Submission to ActivityNet Challenge 2016","date":"2016-08-02","arxiv_id":"1608.00797","repositories_listed":1,"syntology":null}],"record_sha256":"89e68e9cad7c4f6b28fa2d0a9b07e958ad70f55126ffe8eeb8598bb65c0f8084","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}