{"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/temporal-generative-adversarial-nets-with","title":"Temporal Generative Adversarial Nets with Singular Value Clipping","arxiv_id":"1611.06624","date":"2016-11-21","proceeding":"ICCV 2017 10","authors":["Masaki Saito","Eiichi Matsumoto","Shunta Saito"],"abstract":"In this paper, we propose a generative model, Temporal Generative Adversarial\nNets (TGAN), which can learn a semantic representation of unlabeled videos, and\nis capable of generating videos. Unlike existing Generative Adversarial Nets\n(GAN)-based methods that generate videos with a single generator consisting of\n3D deconvolutional layers, our model exploits two different types of\ngenerators: a temporal generator and an image generator. The temporal generator\ntakes a single latent variable as input and outputs a set of latent variables,\neach of which corresponds to an image frame in a video. The image generator\ntransforms a set of such latent variables into a video. To deal with\ninstability in training of GAN with such advanced networks, we adopt a recently\nproposed model, Wasserstein GAN, and propose a novel method to train it stably\nin an end-to-end manner. The experimental results demonstrate the effectiveness\nof our methods.","url_abs":"http://arxiv.org/abs/1611.06624v3","url_pdf":"http://arxiv.org/pdf/1611.06624v3.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":"temporal-generative-adversarial-nets-with","repo_url":"https://github.com/pfnet-research/tgan","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"temporal-generative-adversarial-nets-with","repo_url":"https://github.com/pfnet-research/tgan2","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"temporal-generative-adversarial-nets-with","repo_url":"https://github.com/robbergen/trgan","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"temporal-generative-adversarial-nets-with","repo_url":"https://github.com/universome/stylegan-v","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"video-generation","task_name":"Video Generation"}],"methods":[{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"kaiming-initialization","method_name":"Kaiming Initialization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"rmsprop","method_name":"RMSProp"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"singular-value-clipping","method_name":"Singular Value Clipping"},{"method_slug":"tgan","method_name":"TGAN"},{"method_slug":"tanh-activation","method_name":"Tanh Activation"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/video-generation-on-ucf-101-16-frames-64x64","task":"Video Generation","dataset":"UCF-101 16 frames, 64x64, Unconditional","model":"TGAN-SVC","rank_in_archive_order":6,"of":7,"metrics":{"Inception Score":"11.85"},"uses_additional_data":false},{"leaderboard":"/sota/video-generation-on-ucf-101-16-frames","task":"Video Generation","dataset":"UCF-101 16 frames, Unconditional, Single GPU","model":"TGAN-SVC","rank_in_archive_order":6,"of":7,"metrics":{"Inception Score":"11.85"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/1611.06624","atlas_url":"https://app.syntology.ai/?focus=1611.06624","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1611.06624"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/universome/stylegan-v","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/pfnet-research/tgan2","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/robbergen/trgan","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/pfnet-research/tgan","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":3},"by_repo_kind":{"listed":{"samples":3,"ran":0,"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":0,"samples":[{"code_sha256_prefix":"34833102feafbe30","entry":"calc_inception","repo":"robbergen/trgan","repo_kind":"listed","path":"evaluation/calc_inception.py","file_url":"https://github.com/robbergen/trgan/blob/HEAD/evaluation/calc_inception.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":"34833102feafbe30"}},{"code_sha256_prefix":"6c2f1674b8340103","entry":"calc_inception","repo":"robbergen/trgan","repo_kind":"listed","path":"evaluation/tile_prediction.py","file_url":"https://github.com/robbergen/trgan/blob/HEAD/evaluation/tile_prediction.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":"6c2f1674b8340103"}},{"code_sha256_prefix":"94cf68501cf6d38e","entry":"init_logger","repo":"pfnet-research/tgan","repo_kind":"listed","path":"make_ucf101.py","file_url":"https://github.com/pfnet-research/tgan/blob/HEAD/make_ucf101.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":"94cf68501cf6d38e"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}