Papers › Self-Supervised Learning of Audio-Visual Objects from Video

Self-Supervised Learning of Audio-Visual Objects from Video

10 Aug 2020ECCV 2020 8arXiv:2008.04237archive 2025-07-28

Triantafyllos Afouras, Andrew Owens, Joon Son Chung, Andrew Zisserman

Our objective is to transform a video into a set of discrete audio-visual objects using self-supervised learning. To this end, we introduce a model that uses attention to localize and group sound sources, and optical flow to aggregate information over time. We demonstrate the effectiveness of the audio-visual object embeddings that our model learns by using them for four downstream speech-oriented tasks: (a) multi-speaker sound source separation, (b) localizing and tracking speakers, (c) correcting misaligned audio-visual data, and (d) active speaker detection. Using our representation, these tasks can be solved entirely by training on unlabeled video, without the aid of object detectors. We also demonstrate the generality of our method by applying it to non-human speakers, including cartoons and puppets.Our model significantly outperforms other self-supervised approaches, and obtains performance competitive with methods that use supervised face detection.

PaperPDFConference PDFCodeCode 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 14 code samples harvested from 1 repository linked to this paper: 11 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code; here there are none.

By repository: community (archive-listed): 14 samples from 1 repository, 11 ran (11 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 on 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

afourast/avobjects mentioned on GitHubpytorchMITSyntology: 14 samples, 11 ran (0 instrument-failed) · 3 unverified 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

14 samples harvested: 11 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 0 where Syntology's instrument failed) · 3 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.

11ran
3unverified

Licence: 0 of the 14 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 afourast/avobjects. “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.

afourast/avobjects community (archive-listed) 14 samples, 11 ran (0 instrument-failed) · 3 unverified
Backward in 6 papers flow/pwcnet.py ran fingerprinted MIT (permissive) · 69a7d0834579bdbd · report fixture: signature tensorInput:Tensor/4/float, tensorFlow:Tensor/4/float · returned Tensor · level recorded 2026-09-24
calc_receptive_field utils.py ran MIT (permissive) · fef192e75c60a68c · report fixture: signature layers:list/1/dict, imsize:int/0/int, layer_names:list/1/str · returned tuple · level recorded 2026-09-24
calc_up_down_strides sepnet.py ran fingerprinted MIT (permissive) · 9fb9b2b48e146b7a · report fixture: signature num_layers:int/0/int, stride:int/0/int · returned list · level recorded 2026-09-24
gpu_initializer utils.py ran MIT (permissive) · 67ccf701131b0af7 · report fixture: signature gpu_id:int/0/int · returned device · level recorded 2026-09-24
load_wav in 14 papers load_audio.py ran MIT (permissive) · 33b1b8298f952f5b · report fixture: signature path:str/0/str, fr:int/0/int, to:int/0/int, sample_rate:int/0/int · returned ndarray · level recorded 2026-09-24
normalize_img in 12 papers viz_utils.py ran fingerprinted MIT (permissive) · e7357eb51f7bea31 · report fixture: signature value:Tensor/2/float, vmax:NoneType/0/?, vmin:NoneType/0/? · returned Tensor · level recorded 2026-09-24
outFromIn utils.py ran MIT (permissive) · 616702d60caf4dcd · report fixture: signature conv:tuple/1/int, layerIn:tuple/1/int, ceil_mode:bool/0/bool · returned tuple · level recorded 2026-09-24
relative_module aolib_p3/areload.py ran MIT (permissive) · 695621820eee0aee · report fixture: signature m:module/0/? · returned bool · level recorded 2026-09-24
tensor_from_im flow/pwcnet.py ran fingerprinted MIT (permissive) · 64bc62b1a123906a · report fixture: signature im:ndarray/3/int · returned Tensor · level recorded 2026-09-24
torch_mag_phase_2_np_complex load_audio.py ran MIT (permissive) · 0b0f46b99a26aeb4 · report fixture: signature mag_spect:Tensor/2/float, phase:Tensor/2/float · returned ndarray · level recorded 2026-09-24
viz_boxes_with_scores viz_utils.py ran MIT (permissive) · 71c1d1306fe15964 · report fixture: signature video:ndarray/4/int, box_centers:ndarray/3/float, scores:ndarray/2/float, const_box_size:int/0/int, colors:NoneType/0/?, asd_thresh:float/0/float · returned ndarray · level recorded 2026-09-24
estimate in 14 papers flow/pwcnet.py unverified MIT (permissive) · 0747b9a053d42ac4 · report
load_mp4 load_video.py unverified MIT (permissive) · e71c25d54b32ce0e · report
load_mp4_ffmpeg load_video.py unverified MIT (permissive) · df22707a0588254b · report

Tasks

Active Speaker DetectionFace DetectionOptical Flow EstimationSelf-Supervised Learning

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

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