A Shared Latent for Partially-Labeled Multi-Task Facial Affect Recognition

• URL: http://arxiv.org/abs/2607.16285v1
• Date: Sat, 11 Jul 2026 04:55:12 GMT
• Title: A Shared Latent for Partially-Labeled Multi-Task Facial Affect Recognition
• Abstract summary: We show that partially-labeled multi-task learning is marginalization over a shared affect latent.<n>On s-Aff-Wild2, where only 37% of frames carry all three labels, the classes are severely imbalanced.<n>As each task's source is chosen on the evaluation split, we report the assembled result.
• Score: 9.736740880077823
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Facial affect in the wild is naturally multi-task: valence-arousal, discrete expressions, and facial action units describe the same face. Yet real corpora annotate these tasks only partially and unevenly, so most systems mask the missing labels or impute pseudo-labels and forgo the cross-task signal. We instead cast partially-labeled multi-task learning as marginalization over a shared affect latent: one variational bottleneck mediates all three task decoders, so a frame annotated for one task shapes the representation the others use, and the masked objective reappears as the reconstruction term of an evidence lower bound. On s-Aff-Wild2, where only 37% of frames carry all three labels, the classes are severely imbalanced, and pretraining on the source data is disallowed, we isolate where this coupling acts. On a single backbone it lifts expression macro-F1 from 0.403 for a dedicated specialist to 0.446, which the masked-loss model does not reach; a second, near-peer backbone with decorrelated errors then breaks an action-unit ceiling that external action-unit data could not, while valence-arousal stays within noise. Every gain is disciplined by a matched-control negative; together these controls indicate that the rare-class failure is representational, not a matter of loss shaping. As each task's source is chosen on the evaluation split, we report the assembled result, a combined multi-task score of 1.679 on validation, as an in-sample endpoint and rest our conclusions on the controlled comparisons; a small, regime-dependent transfer of the expression advantage to AffectNet and RAF-DB is presented as exploratory rather than conclusive.

Related papers

• The Intervention Gap in Latent World Models [0.0]
  Planning-time intervention fidelity is a distinct, measurable property of a learned world model.<n>Across released TD-MPC2 checkpoint sizes, episode return falls as an operator-error diagnostic on task observables grows.<n>A self-supervised world model trained without task signal preserves the same operator substantially better than a task-anchored model on the shared task.
  arXiv  Detail & Related papers  (2026-08-30T19:47:51Z)
• Multi-Agent Target-Existence Verification and Learned Mask Geometry Refinement: Winning Report of the MeViS-Text Track at the 8th LSVOS Challenge 2026 [0.6416429054645992]
  We present the first-place solution to the MeViS-Text track of the 8th Large-scale Video Object (LSVOS) Challenge 2026.<n> referring video object segmentation guided by written motion expressions, including deceptive no-target expressions.<n>Our pipeline, SSUPER, resolves each expression into a visual concept, generates full-video candidate masklets with SAM3.1, and selects target IDs.
  arXiv  Detail & Related papers  (2026-08-11T21:47:52Z)
• When Does Consensus Mean Correctness? Measuring the Agreement-Accuracy Coupling with Semantics-Preserving Re-Rendering [0.8594140167290097]
  A model's agreement across perturbed inputs is used as a label-free reliability signal.<n>Rerendering beats resampling on both accuracy and reliability.<n>Fine-tuning on the model's own cross-render consensus inverts.
  arXiv  Detail & Related papers  (2026-08-06T07:08:05Z)
• Suppression Sticks, Locality Is Fragile: A Closed-Loop Target-and-Control Audit of Task-Vector Negation in VLA Policies [33.432377306905735]
  Task-vector arithmetic offers a closed-form way to modify a model, yet its behavioral locality remains unclear in closed-loop robot control.<n>We present a target-and-control audit of per-skill task-vector subtraction from multitask vision-language-action (VLA) policies.
  arXiv  Detail & Related papers  (2026-08-05T10:59:53Z)
• DisPOSE: Projected Polystochastic Diffusion for Self-Supervised Multi-View 3D Human Pose Estimation [58.47973015036709]
  DisPOSE is a self-supervised framework that approximates the inherently discrete multi-view person-assignment problem.<n>By employing differentiable Sinkhorn projections during denoising, our model learns to guide solutions toward valid and feasible assignments.<n>The proposed approach outperforms current state-of-the-art self-supervised methods on standard datasets.
  arXiv  Detail & Related papers  (2026-06-05T16:14:39Z)
• Task-Guided Multi-Annotation Triplet Learning for Remote Sensing Representations [2.5700571547896103]
  Prior triplet loss methods relied on static weights to balance supervision between various types of annotation.<n>The proposed task-guided triplet loss removes this dependency by selecting triplets through a mutual-information criteria.<n>Experiments show that task-aware triplet selection produces a more effective shared representation for downstream tasks.
  arXiv  Detail & Related papers  (2026-04-04T19:30:38Z)
• Multi-threshold Deep Metric Learning for Facial Expression Recognition [60.26967776920412]
  We present the multi-threshold deep metric learning technique, which avoids the difficult threshold validation. We find that each threshold of the triplet loss intrinsically determines a distinctive distribution of inter-class variations. It makes the embedding layer, which is composed of a set of slices, a more informative and discriminative feature.
  arXiv  Detail & Related papers  (2024-06-24T08:27:31Z)
• Localizing Task Information for Improved Model Merging and Compression [61.16012721460561]
  We show that the information required to solve each task is still preserved after merging as different tasks mostly use non-overlapping sets of weights. We propose Consensus Merging, an algorithm that eliminates such weights and improves the general performance of existing model merging approaches.
  arXiv  Detail & Related papers  (2024-05-13T14:54:37Z)
• Towards A Robust Group-level Emotion Recognition via Uncertainty-Aware Learning [27.284076257222942]
  Group-level emotion recognition (GER) is an inseparable part of human behavior analysis.<n>We propose an uncertainty-aware learning (UAL) method to extract more robust representations for GER.<n>We develop an image enhancement module to enhance the model's robustness against severe noise.
  arXiv  Detail & Related papers  (2023-10-06T15:05:41Z)
• Leveraging sparse and shared feature activations for disentangled representation learning [112.22699167017471]
  We propose to leverage knowledge extracted from a diversified set of supervised tasks to learn a common disentangled representation. We validate our approach on six real world distribution shift benchmarks, and different data modalities.
  arXiv  Detail & Related papers  (2023-04-17T01:33:24Z)
• Uncertain Facial Expression Recognition via Multi-task Assisted Correction [43.02119884581332]
  We propose a novel method of multi-task assisted correction in addressing uncertain facial expression recognition called MTAC. Specifically, a confidence estimation block and a weighted regularization module are applied to highlight solid samples and suppress uncertain samples in every batch. Experiments on RAF-DB, AffectNet, and AffWild2 datasets demonstrate that the MTAC obtains substantial improvements over baselines when facing synthetic and real uncertainties.
  arXiv  Detail & Related papers  (2022-12-14T10:28:08Z)
• Joint-Modal Label Denoising for Weakly-Supervised Audio-Visual Video Parsing [52.2231419645482]
  This paper focuses on the weakly-supervised audio-visual video parsing task. It aims to recognize all events belonging to each modality and localize their temporal boundaries.
  arXiv  Detail & Related papers  (2022-04-25T11:41:17Z)
• Exploiting Sample Uncertainty for Domain Adaptive Person Re-Identification [137.9939571408506]
  We estimate and exploit the credibility of the assigned pseudo-label of each sample to alleviate the influence of noisy labels. Our uncertainty-guided optimization brings significant improvement and achieves the state-of-the-art performance on benchmark datasets.
  arXiv  Detail & Related papers  (2020-12-16T04:09:04Z)
• Disentanglement for Discriminative Visual Recognition [7.954325638519141]
  This chapter systematically summarize the detrimental factors as task-relevant/irrelevant semantic variations and unspecified latent variation. The better FER performance can be achieved by combining the deep metric loss and softmax loss in a unified two fully connected layer branches framework. The framework achieves top performance on a serial of tasks, including lighting, makeup, disguise-tolerant face recognition and facial attributes recognition.
  arXiv  Detail & Related papers  (2020-06-14T06:10:51Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.