ACE: Action Concept Enhancement of Video-Language Models in Procedural Videos

• URL: http://arxiv.org/abs/2411.15628v1
• Date: Sat, 23 Nov 2024 18:49:49 GMT
• Title: ACE: Action Concept Enhancement of Video-Language Models in Procedural Videos
• Abstract summary: Action Concept Enhancement (ACE) improves concept understanding of vision-language models (VLMs) ACE continually incorporates augmented action synonyms and negatives in an auxiliary classification loss. We show the enhanced concept understanding of our VLM, by visualizing the alignment of encoded embeddings of unseen action synonyms in the embedding space.
• Score: 7.030989629685138
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Vision-language models (VLMs) are capable of recognizing unseen actions. However, existing VLMs lack intrinsic understanding of procedural action concepts. Hence, they overfit to fixed labels and are not invariant to unseen action synonyms. To address this, we propose a simple fine-tuning technique, Action Concept Enhancement (ACE), to improve the robustness and concept understanding of VLMs in procedural action classification. ACE continually incorporates augmented action synonyms and negatives in an auxiliary classification loss by stochastically replacing fixed labels during training. This creates new combinations of action labels over the course of fine-tuning and prevents overfitting to fixed action representations. We show the enhanced concept understanding of our VLM, by visualizing the alignment of encoded embeddings of unseen action synonyms in the embedding space. Our experiments on the ATA, IKEA and GTEA datasets demonstrate the efficacy of ACE in domains of cooking and assembly leading to significant improvements in zero-shot action classification while maintaining competitive performance on seen actions.

Related papers

• TF-CADE: Foreground-Concentrated Text-Video Alignment for Zero-Shot Temporal Action Detection [54.38725298163703]
  We propose a Text-Foreground Concentrated Alignment for zero-shot temporal action DEtector (TF-CADE)<n>ACA extracts action concentrate scores to aggregate temporally informative video segments into a foreground- weighted video embedding.<n> CCR strategy refines per-snippet confidence scores by lever- aging foreground-aware similarity, effectively suppressing irrelevant action classes during inference.
  arXiv  Detail & Related papers  (2026-08-18T06:43:45Z)
• CAC-VLA: Context-Gated Action Conditioning for Vision-Language-Action Models [22.159641172687884]
  Vision-Language-Action (VLA) models have become a promising paradigm for generalist robot manipulation.<n>We propose CAC-VLA, a Context-Gated Action Conditioning framework that learns a lightweight latent-action interface directly within the VLM.<n>Experiments on LIBERO and LIBERO-Plus demonstrate the effectiveness of CAC-VLA, achieving 98.3% average success rate.
  arXiv  Detail & Related papers  (2026-07-06T08:50:05Z)
• QuoVLA: Quotient Space for Vision-Language-Action Models [51.02329790939691]
  Vision-Language-Action (VLA) models commonly adapt pretrained VLM latents to robot control by mapping visual observations and language instructions to continuous actions.<n>Our textitQuotient Theory for VLA shows that pretrained VLM latents are not action-insufficient but action-sufficient.<n>We propose QuoVLA, a quotient-space framework for VLA that compresses pretrained VLM latents into action-sufficient representations.
  arXiv  Detail & Related papers  (2026-05-24T06:28:53Z)
• Afford-VLA: Action-Aligned Visual Planning via Internalized Affordance [108.46436073194546]
  We argue that effective planning should be local, visually grounded, internally generated, and directly aligned with action.<n>We propose Afford-VLA, a unified framework that internalizes task-conditioned affordance as an explicit visual planning interface within VLA models.
  arXiv  Detail & Related papers  (2026-05-22T20:43:47Z)
• Motion-Guided Semantic Alignment with Negative Prompts for Zero-Shot Video Action Recognition [12.523217686212197]
  We present a novel framework that enhances CLIP with disentangled embeddings and semantic-guided interaction.<n>Experiments on standard benchmarks demonstrate that our method consistently outperforms prior CLIP-based approaches.
  arXiv  Detail & Related papers  (2026-04-18T16:34:29Z)
• Learning Additively Compositional Latent Actions for Embodied AI [29.26703392827422]
  Latent action learning infers pseudo-action labels from visual transitions.<n>We introduce Additively Compositional Latent Action Model (AC-LAM)<n>AC-LAM enforces scene-wise additive composition structure over short horizons on the latent action space.
  arXiv  Detail & Related papers  (2026-04-03T08:53:29Z)
• \ extsc{NaVIDA}: Vision-Language Navigation with Inverse Dynamics Augmentation [50.027425808733994]
  textscNaVIDA is a unified VLN framework that couples policy learning with action-grounded visual dynamics and adaptive execution.<n>textscNaVIDA augments training with chunk-based inverse-dynamics supervision to learn causal relationship between visual changes and corresponding actions.<n>Experiments show that textscNaVIDA achieves superior navigation performance compared to state-of-the-art methods with fewer parameters.
  arXiv  Detail & Related papers  (2026-01-26T06:16:17Z)
• PosA-VLA: Enhancing Action Generation via Pose-Conditioned Anchor Attention [92.85371254435074]
  PosA-VLA framework anchors visual attention via pose-conditioned supervision, consistently guiding the model's perception toward task-relevant regions.<n>We show that our method executes embodied tasks with precise and time-efficient behavior across diverse robotic manipulation benchmarks.
  arXiv  Detail & Related papers  (2025-12-03T12:14:29Z)
• Zero-Shot Open-Vocabulary Human Motion Grounding with Test-Time Training [39.7658823121591]
  ZOMG is a framework that segments motion sequences into semantically meaningful sub-actions without requiring any annotations or fine-tuning.<n>ZOMG integrates (1) language semantic partition, which leverages large language models to decompose instructions into ordered sub-action units, and (2) soft masking optimization.<n>Experiments on three motion-language datasets demonstrate state-of-the-art effectiveness and efficiency of motion grounding performance, outperforming prior methods by +8.7% mAP on HumanML3D benchmark.
  arXiv  Detail & Related papers  (2025-11-19T12:11:36Z)
• Towards Fine-Grained Adaptation of CLIP via a Self-Trained Alignment Score [11.74414842618874]
  We show that modeling fine-grained cross-modal interactions during adaptation produces more accurate, class-discriminative pseudo-labels.<n>We introduce Fine-grained Alignment and Interaction Refinement (FAIR), an innovative approach that dynamically aligns localized image features with descriptive language embeddings.<n>Our approach, FAIR, delivers a substantial performance boost in fine-grained unsupervised adaptation, achieving a notable overall gain of 2.78%.
  arXiv  Detail & Related papers  (2025-07-13T12:38:38Z)
• Object-Centric Latent Action Learning [70.3173534658611]
  We propose a novel object-centric latent action learning framework that centers on objects rather than pixels.<n>We leverage self-supervised object-centric pretraining to disentangle action-related and distracting dynamics.<n>Our results show that object-centric pretraining mitigates the negative effects of distractors by 50%.
  arXiv  Detail & Related papers  (2025-02-13T11:27:05Z)
• FinePseudo: Improving Pseudo-Labelling through Temporal-Alignablity for Semi-Supervised Fine-Grained Action Recognition [57.17966905865054]
  Real-life applications of action recognition often require a fine-grained understanding of subtle movements. Existing semi-supervised action recognition has mainly focused on coarse-grained action recognition. We propose an Alignability-Verification-based Metric learning technique to effectively discriminate between fine-grained action pairs.
  arXiv  Detail & Related papers  (2024-09-02T20:08:06Z)
• An Information Compensation Framework for Zero-Shot Skeleton-based Action Recognition [49.45660055499103]
  Zero-shot human skeleton-based action recognition aims to construct a model that can recognize actions outside the categories seen during training. Previous research has focused on aligning sequences' visual and semantic spatial distributions. We introduce a new loss function sampling method to obtain a tight and robust representation.
  arXiv  Detail & Related papers  (2024-06-02T06:53:01Z)
• Language-Driven Visual Consensus for Zero-Shot Semantic Segmentation [114.72734384299476]
  We propose a Language-Driven Visual Consensus (LDVC) approach, fostering improved alignment of semantic and visual information. We leverage class embeddings as anchors due to their discrete and abstract nature, steering vision features toward class embeddings. Our approach significantly boosts the capacity of segmentation models for unseen classes.
  arXiv  Detail & Related papers  (2024-03-13T11:23:55Z)
• Cross-Video Contextual Knowledge Exploration and Exploitation for Ambiguity Reduction in Weakly Supervised Temporal Action Localization [23.94629999419033]
  Weakly supervised temporal action localization (WSTAL) aims to localize actions in untrimmed videos using video-level labels. Our work addresses this from a novel perspective, by exploring and exploiting the cross-video contextual knowledge within the dataset. Our method outperforms the state-of-the-art methods, and can be easily plugged into other WSTAL methods.
  arXiv  Detail & Related papers  (2023-08-24T07:19:59Z)
• Action Sensitivity Learning for Temporal Action Localization [35.65086250175736]
  We propose an Action Sensitivity Learning framework (ASL) to tackle the task of temporal action localization. We first introduce a lightweight Action Sensitivity Evaluator to learn the action sensitivity at the class level and instance level, respectively. Based on the action sensitivity of each frame, we design an Action Sensitive Contrastive Loss to enhance features, where the action-aware frames are sampled as positive pairs to push away the action-irrelevant frames.
  arXiv  Detail & Related papers  (2023-05-25T04:19:14Z)
• Weakly-Supervised Temporal Action Localization with Bidirectional Semantic Consistency Constraint [83.36913240873236]
  Weakly Supervised Temporal Action localization (WTAL) aims to classify and localize temporal boundaries of actions for the video. We propose a simple yet efficient method, named bidirectional semantic consistency constraint (Bi- SCC) to discriminate the positive actions from co-scene actions. Experimental results show that our approach outperforms the state-of-the-art methods on THUMOS14 and ActivityNet.
  arXiv  Detail & Related papers  (2023-04-25T07:20:33Z)
• Fine-grained Temporal Contrastive Learning for Weakly-supervised Temporal Action Localization [87.47977407022492]
  This paper argues that learning by contextually comparing sequence-to-sequence distinctions offers an essential inductive bias in weakly-supervised action localization. Under a differentiable dynamic programming formulation, two complementary contrastive objectives are designed, including Fine-grained Sequence Distance (FSD) contrasting and Longest Common Subsequence (LCS) contrasting. Our method achieves state-of-the-art performance on two popular benchmarks.
  arXiv  Detail & Related papers  (2022-03-31T05:13:50Z)
• Elaborative Rehearsal for Zero-shot Action Recognition [36.84404523161848]
  ZSAR aims to recognize target (unseen) actions without training examples. It remains challenging to semantically represent action classes and transfer knowledge from seen data. We propose an ER-enhanced ZSAR model inspired by an effective human memory technique Elaborative Rehearsal.
  arXiv  Detail & Related papers  (2021-08-05T20:02:46Z)
• Learning to Recognize Actions on Objects in Egocentric Video with Attention Dictionaries [51.48859591280838]
  We present EgoACO, a deep neural architecture for video action recognition. It learns to pool action-context-object descriptors from frame level features. Cap uses self-attention with a dictionary of learnable weights to pool from the most relevant feature regions.
  arXiv  Detail & Related papers  (2021-02-16T10:26:04Z)

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.