Papers › Learning Emotion Representations from Verbal and Nonverbal Communication

Learning Emotion Representations from Verbal and Nonverbal Communication

22 May 2023CVPR 2023 1arXiv:2305.13500archive 2025-07-28

Sitao Zhang, Yimu Pan, James Z. Wang

Emotion understanding is an essential but highly challenging component of artificial general intelligence. The absence of extensively annotated datasets has significantly impeded advancements in this field. We present EmotionCLIP, the first pre-training paradigm to extract visual emotion representations from verbal and nonverbal communication using only uncurated data. Compared to numerical labels or descriptions used in previous methods, communication naturally contains emotion information. Furthermore, acquiring emotion representations from communication is more congruent with the human learning process. We guide EmotionCLIP to attend to nonverbal emotion cues through subject-aware context encoding and verbal emotion cues using sentiment-guided contrastive learning. Extensive experiments validate the effectiveness and transferability of EmotionCLIP. Using merely linear-probe evaluation protocol, EmotionCLIP outperforms the state-of-the-art supervised visual emotion recognition methods and rivals many multimodal approaches across various benchmarks. We anticipate that the advent of EmotionCLIP will address the prevailing issue of data scarcity in emotion understanding, thereby fostering progress in related domains. The code and pre-trained models are available at https://github.com/Xeaver/EmotionCLIP.

PaperPDFConference PDFCodeCode Syntology ran

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

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2305.13500")

Code

Syntology Ran 10 of 29 code samples harvested from 1 repository linked to this paper; 19 have no recorded run. Of those that ran: 2 ran · our draft was wrong; 8 ran with no contract checked.

By repository: official repository: 29 samples from 1 repository, 10 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

xeaver/emotionclip officialmentioned in paperpytorchMIT 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

29 samples harvested; 10 ran; 0 honoured the contract we drafted; 19 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

2ran · our draft was wrong
8ran
19unverified

Licence: 0 of the 29 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 Xeaver/EmotionCLIP. “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. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (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 from a repository marked official are listed first. 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 four 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; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). 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.

AttentionPool2d Xeaver/EmotionCLIP/src/models/base.py official repository ran MIT (permissive) · c31ea380cbe12461 · report
Bottleneck Xeaver/EmotionCLIP/src/models/base.py official repository ran fingerprinted MIT (permissive) · 317eeb922af6df8c · report
CLIPVisionCfg Xeaver/EmotionCLIP/src/models/base.py official repository ran MIT (permissive) · 147cc99e5a62df69 · report
LayerNorm Xeaver/EmotionCLIP/src/models/base.py official repository ran · metamorphic tier: invariant fingerprinted MIT (permissive) · 521eb383ee0b590c · report
ResidualAttentionBlock Xeaver/EmotionCLIP/src/models/base.py official repository ran MIT (permissive) · 72ae1815d1a81517 · report
Transformer Xeaver/EmotionCLIP/src/models/base.py official repository ran MIT (permissive) · 698e12b8a3909d01 · report
VisualHead Xeaver/EmotionCLIP/src/models/base.py official repository ran MIT (permissive) · 02d6e69496cfde7c · report
VisualTransformer Xeaver/EmotionCLIP/src/models/base.py official repository ran MIT (permissive) · c857cf6246801938 · report
_ntuple Xeaver/EmotionCLIP/src/models/base.py official repository ran · our draft was wrong MIT (permissive) · ee61c52d701d0844 · report
freeze_batch_norm_2d Xeaver/EmotionCLIP/src/models/base.py official repository ran · our draft was wrong MIT (permissive) · 4414627a34d3f5a6 · report
CLIP Xeaver/EmotionCLIP/src/models/base.py official repository unverified MIT (permissive) · bd68a70f00670d88 · report
DefaultDataLoader xeaver/emotionclip/linear_eval.py official repository unverified MIT (permissive) · 4e3b3a6334554db6 · report
EmotionCLIP Xeaver/EmotionCLIP/src/models/base.py official repository unverified MIT (permissive) · 83d96ef6b277e8b1 · report
ModifiedResNet Xeaver/EmotionCLIP/src/models/base.py official repository unverified MIT (permissive) · e16cbf2cae362701 · report
accuracy_from_affect2mm xeaver/emotionclip/linear_eval.py official repository unverified MIT (permissive) · 304f8d104c3ae85b · report
bbox_to_mask xeaver/emotionclip/src/datasets/bold.py official repository unverified MIT (permissive) · 22f55504153a6c4a · report
create_index xeaver/emotionclip/preprocessing/create_index.py official repository unverified MIT (permissive) · 5117c4f71e3e05f2 · report
filter_frames_by_subs xeaver/emotionclip/preprocessing/download_videos.py official repository unverified MIT (permissive) · 908004750488edf4 · report
frames_to_hdf5 xeaver/emotionclip/preprocessing/frames_to_hdf5.py official repository unverified MIT (permissive) · 982a5d4308b89326 · report
get_correct_bbox xeaver/emotionclip/src/datasets/emotic.py official repository unverified MIT (permissive) · fffd8407fb58896e · report
get_word_time_range xeaver/emotionclip/preprocessing/regroup_transcripts.py official repository unverified MIT (permissive) · 8fce15b73d85523c · report
is_path_writable xeaver/emotionclip/src/utils.py official repository unverified MIT (permissive) · ea7b78f323af0b60 · report
joints_to_bbox xeaver/emotionclip/src/datasets/bold.py official repository unverified MIT (permissive) · 617c4c27e5687338 · report
regroup_by_punc xeaver/emotionclip/preprocessing/regroup_transcripts.py official repository unverified MIT (permissive) · 507b8fae3df11365 · report
remove_unuseful_frames xeaver/emotionclip/preprocessing/download_videos.py official repository unverified MIT (permissive) · a13c7ce400fe0bd9 · report
search_playlist xeaver/emotionclip/preprocessing/search_youtube.py official repository unverified MIT (permissive) · 4a6f84446e0450a6 · report
tar_gz_to_hdf5 xeaver/emotionclip/preprocessing/frames_to_hdf5.py official repository unverified MIT (permissive) · 7433c55c64017801 · report
timeit xeaver/emotionclip/src/utils.py official repository unverified MIT (permissive) · e037cf75b0da50f6 · report
with_timer xeaver/emotionclip/src/utils.py official repository unverified MIT (permissive) · 6907192b23bf18d8 · report

Tasks

Contrastive LearningEmotion RecognitionEmotion Recognition in Context

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Emotion Recognition in Context BoLD EmotionCLIP(linear-probe evaluation) AUC 69.30 #2 of 3 Archive leaderboard report
Emotion Recognition in Context BoLD EmotionCLIP(linear-probe evaluation) Average mAP 22.51 #2 of 3 Archive leaderboard report
Emotion Recognition in Context EMOTIC EmotionCLIP(linear-probe evaluation) mAP 32.91 #3 of 9 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