Papers › TransNet V2: An effective deep network architecture for fast shot transition detection

TransNet V2: An effective deep network architecture for fast shot transition detection

11 Aug 2020arXiv:2008.04838archive 2025-07-28

Tomáš Souček, Jakub Lokoč

Although automatic shot transition detection approaches are already investigated for more than two decades, an effective universal human-level model was not proposed yet. Even for common shot transitions like hard cuts or simple gradual changes, the potential diversity of analyzed video contents may still lead to both false hits and false dismissals. Recently, deep learning-based approaches significantly improved the accuracy of shot transition detection using 3D convolutional architectures and artificially created training data. Nevertheless, one hundred percent accuracy is still an unreachable ideal. In this paper, we share the current version of our deep network TransNet V2 that reaches state-of-the-art performance on respected benchmarks. A trained instance of the model is provided so it can be instantly utilized by the community for a highly efficient analysis of large video archives. Furthermore, the network architecture, as well as our experience with the training process, are detailed, including simple code snippets for convenient usage of the proposed model and visualization of results.

PaperPDFCodeCode Syntology ran

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 15 code samples harvested from 2 repositories linked to this paper: 13 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 0 honoured, 0 violated, 13 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code; here there are none.

By repository: official repository: 12 samples from 1 repository, 11 ran (11 with no instrument failure; 0 where Syntology's instrument failed); community (archive-listed): 3 samples from 1 repository, 2 ran (2 with no instrument failure; 0 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Levels written between 2026-09-24 and 2026-09-26 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

soCzech/TransNetV2 officialmentioned in papermentioned on GitHubtfMITSyntology: 12 samples, 11 ran (0 instrument-failed) · 1 unverified report
shallwe999/TransNetV2-SBD-Visualize mentioned on GitHubtfMITSyntology: 3 samples, 2 ran (0 instrument-failed) · 1 unverified report
soCzech/MasterThesis mentioned on GitHubSyntology: not harvested report
wqliu657/TransNetV2 mentioned on GitHubtfMITSyntology: not harvested report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

15 samples harvested: 13 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 0 honoured, 0 violated, 13 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

13ran
2unverified

Licence: 0 of the 15 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 2 repositories linked to this paper, official or community; the list below is grouped by repository, each group headed by its name and what it is to the paper. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: 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. Samples are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of six reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity.

soCzech/TransNetV2 official repository 12 samples, 11 ran (0 instrument-failed) · 1 unverified
check_and_fix_dicts inference-pytorch/convert_weights.py ran MIT (permissive) · 7af38278c93d587f · report fixture: signature tf_dict:dict/0/?, torch_dict:dict/0/? · returned bool · level recorded 2026-09-25
compute_normalization_fixed_point in 5 papers training/bi_tempered_loss.py ran MIT (permissive) · cec13b69d85253c3 · report fixture: signature activations:EagerTensor/2/float, t:EagerTensor/0/float, num_iters:int/0/int · returned EagerTensor · level recorded 2026-09-25
evaluate_scenes training/metrics_utils.py ran MIT (permissive) · 8b38bd5a0be9bce7 · report fixture: signature gt_scenes:ndarray/2/int, pred_scenes:ndarray/2/int, return_mistakes:bool/0/bool, n_frames_miss_tolerance:int/0/int · returned tuple · level recorded 2026-09-25
exp_t in 5 papers training/bi_tempered_loss.py ran MIT (permissive) · a6d36281c438e25b · report fixture: signature u:EagerTensor/2/float, t:EagerTensor/0/float · returned EagerTensor · level recorded 2026-09-25
get_batches in 12 papers training/evaluate.py ran MIT (permissive) · 7d243f22f59049e3 · report fixture: signature frames:ndarray/3/float · returned generator · level recorded 2026-09-26
get_scenes_from_transition_frames training/consolidate_datasets.py ran fingerprinted MIT (permissive) · a574b706c69a2e4a · report fixture: signature transition_frames:ndarray/1/int, video_len:int/0/int · returned ndarray · level recorded 2026-09-25
log_t in 5 papers training/bi_tempered_loss.py ran MIT (permissive) · e047237f9926614c · report fixture: signature u:EagerTensor/1/float, t:EagerTensor/0/float · returned EagerTensor · level recorded 2026-09-25
predictions_to_scenes training/metrics_utils.py ran MIT (permissive) · 3da0df168740c1aa · report fixture: signature predictions:ndarray/1/int · returned ndarray · level recorded 2026-09-25
remap_name inference-pytorch/convert_weights.py ran fingerprinted MIT (permissive) · 61c9ba481effd824 · report fixture: signature x:str/0/str · returned str · level recorded 2026-09-25
remap_tensor inference-pytorch/convert_weights.py ran fingerprinted MIT (permissive) · c35a46af5bf2323c · report fixture: signature x:Tensor/5/float · returned Tensor · level recorded 2026-09-25
scenes2zero_one_representation training/create_dataset.py ran MIT (permissive) · 4f1f9a4527adf939 · report fixture: signature scenes:list/1/tuple, n_frames:int/0/int · returned tuple · level recorded 2026-09-25
graph in 6 papers training/metrics_utils.py unverified MIT (permissive) · c19395bc49d7798c · report
shallwe999/TransNetV2-SBD-Visualize community (archive-listed) 3 samples, 2 ran (0 instrument-failed) · 1 unverified
read_predictions in 8 papers utils.py ran MIT (permissive) · fa843917bfca3cfb · report fixture: signature file_name:str/0/str, split_char:str/0/str · returned list · level recorded 2026-09-24
read_scenes utils.py ran MIT (permissive) · 732def07b44046eb · report fixture: signature file_name:str/0/str, split_char:str/0/str · returned list · level recorded 2026-09-24
main_process in 45 papers transnetv2.py unverified MIT (permissive) · e6c126c38a88b3c8 · report

Tasks

Boundary DetectionCamera shot boundary detectionDiversity

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Camera shot boundary detection ClipShots TransNet V2 F1 score 77.9 #2 of 4 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections