Principles of Visual Tokens for Efficient Video Understanding

Video understanding has made huge strides in recent years, relying largely on the power of the transformer architecture. As this architecture is notoriously expensive and video is highly redundant, research into improving efficiency has become particularly relevant. This has led to many creative solutions, including token merging and token selection. While most methods succeed in reducing the cost of the model and maintaining accuracy, an interesting pattern arises: most methods do not outperform the random sampling baseline. In this paper we take a closer look at this phenomenon and make several observations. First, we develop an oracle for the value of tokens which exposes a clear Pareto distribution where most tokens have remarkably low value, and just a few carry most of the perceptual information. Second, we analyze why this oracle is extremely hard to learn, as it does not consistently coincide with visual cues. Third, we observe that easy videos need fewer tokens to maintain accuracy. We build on these and further insights to propose a lightweight video model we call LITE that can select a small number of tokens effectively, outperforming state-of-the-art and existing baselines across datasets (Kinetics400 and Something-Something-V2) in the challenging trade-off of computation (GFLOPs) vs accuracy.

Continual Learning Improves Zero-Shot Action Recognition

Zero-shot action recognition requires a strong ability to generalize from pre-training and seen classes to novel unseen classes. Similarly, continual learning aims to develop models that can generalize effectively and learn new tasks without forgetting the ones previously learned. The generalization goals of zero-shot and continual learning are closely aligned, however techniques from continual learning have not been applied to zero-shot action recognition. In this paper, we propose a novel method based on continual learning to address zero-shot action recognition. This model, which we call {\em Generative Iterative Learning} (GIL) uses a memory of synthesized features of past classes, and combines these synthetic features with real ones from novel classes. The memory is used to train a classification model, ensuring a balanced exposure to both old and new classes. Experiments demonstrate that {\em GIL} improves generalization in unseen classes, achieving a new state-of-the-art in zero-shot recognition across multiple benchmarks. Importantly, {\em GIL} also boosts performance in the more challenging generalized zero-shot setting, where models need to retain knowledge about classes seen before fine-tuning.

Learning Precise Affordances from Egocentric Videos for Robotic Manipulation

Affordance, defined as the potential actions that an object offers, is crucial for robotic manipulation tasks. A deep understanding of affordance can lead to more intelligent AI systems. For example, such knowledge directs an agent to grasp a knife by the handle for cutting and by the blade when passing it to someone. In this paper, we present a streamlined affordance learning system that encompasses data collection, effective model training, and robot deployment. First, we collect training data from egocentric videos in an automatic manner. Different from previous methods that focus only on the object graspable affordance and represent it as coarse heatmaps, we cover both graspable (e.g., object handles) and functional affordances (e.g., knife blades, hammer heads) and extract data with precise segmentation masks. We then propose an effective model, termed Geometry-guided Affordance Transformer (GKT), to train on the collected data. GKT integrates an innovative Depth Feature Injector (DFI) to incorporate 3D shape and geometric priors, enhancing the model's understanding of affordances. To enable affordance-oriented manipulation, we further introduce Aff-Grasp, a framework that combines GKT with a grasp generation model. For comprehensive evaluation, we create an affordance evaluation dataset with pixel-wise annotations, and design real-world tasks for robot experiments. The results show that GKT surpasses the state-of-the-art by 15.9% in mIoU, and Aff-Grasp achieves high success rates of 95.5% in affordance prediction and 77.1% in successful grasping among 179 trials, including evaluations with seen, unseen objects, and cluttered scenes.

Coarse or Fine? Recognising Action End States without Labels

We focus on the problem of recognising the end state of an action in an image, which is critical for understanding what action is performed and in which manner. We study this focusing on the task of predicting the coarseness of a cut, i.e., deciding whether an object was cut "coarsely" or "finely". No dataset with these annotated end states is available, so we propose an augmentation method to synthesise training data. We apply this method to cutting actions extracted from an existing action recognition dataset. Our method is object agnostic, i.e., it presupposes the location of the object but not its identity. Starting from less than a hundred images of a whole object, we can generate several thousands images simulating visually diverse cuts of different coarseness. We use our synthetic data to train a model based on UNet and test it on real images showing coarsely/finely cut objects. Results demonstrate that the model successfully recognises the end state of the cutting action despite the domain gap between training and testing, and that the model generalises well to unseen objects.

One-Shot Open Affordance Learning with Foundation Models

We introduce One-shot Open Affordance Learning (OOAL), where a model is trained with just one example per base object category, but is expected to identify novel objects and affordances. While vision-language models excel at recognizing novel objects and scenes, they often struggle to understand finer levels of granularity such as affordances. To handle this issue, we conduct a comprehensive analysis of existing foundation models, to explore their inherent understanding of affordances and assess the potential for data-limited affordance learning. We then propose a vision-language framework with simple and effective designs that boost the alignment between visual features and affordance text embeddings. Experiments on two affordance segmentation benchmarks show that the proposed method outperforms state-of-the-art models with less than 1% of the full training data, and exhibits reasonable generalization capability on unseen objects and affordances.

Efficient Pre-training for Localized Instruction Generation of Videos

Procedural videos show step-by-step demonstrations of tasks like recipe preparation. Understanding such videos is challenging, involving the precise localization of steps and the generation of textual instructions. Manually annotating steps and writing instructions is costly, which limits the size of current datasets and hinders effective learning. Leveraging large but noisy video-transcript datasets for pre-training can boost performance, but demands significant computational resources. Furthermore, transcripts contain irrelevant content and exhibit style variation compared to instructions written by human annotators. To mitigate both issues, we propose a technique, Sieve-&-Swap, to automatically curate a smaller dataset: (i) Sieve filters irrelevant transcripts and (ii) Swap enhances the quality of the text instruction by automatically replacing the transcripts with human-written instructions from a text-only recipe dataset. The curated dataset, three orders of magnitude smaller than current web-scale datasets, enables efficient training of large-scale models with competitive performance. We complement our Sieve-\&-Swap approach with a Procedure Transformer (ProcX) for end-to-end step localization and instruction generation for procedural videos. When this model is pre-trained on our curated dataset, it achieves state-of-the-art performance in zero-shot and finetuning settings on YouCook2 and Tasty, while using a fraction of the computational resources.

Watt For What: Rethinking Deep Learning's Energy-Performance Relationship

Deep learning models have revolutionized various fields, from image recognition to natural language processing, by achieving unprecedented levels of accuracy. However, their increasing energy consumption has raised concerns about their environmental impact, disadvantaging smaller entities in research and exacerbating global energy consumption. In this paper, we explore the trade-off between model accuracy and electricity consumption, proposing a metric that penalizes large consumption of electricity. We conduct a comprehensive study on the electricity consumption of various deep learning models across different GPUs, presenting a detailed analysis of their accuracy-efficiency trade-offs. By evaluating accuracy per unit of electricity consumed, we demonstrate how smaller, more energy-efficient models can significantly expedite research while mitigating environmental concerns. Our results highlight the potential for a more sustainable approach to deep learning, emphasizing the importance of optimizing models for efficiency. This research also contributes to a more equitable research landscape, where smaller entities can compete effectively with larger counterparts. This advocates for the adoption of efficient deep learning practices to reduce electricity consumption, safeguarding the environment for future generations whilst also helping ensure a fairer competitive landscape.

Telling Stories for Common Sense Zero-Shot Action Recognition

Video understanding has long suffered from reliance on large labeled datasets, motivating research into zero-shot learning. Recent progress in language modeling presents opportunities to advance zero-shot video analysis, but constructing an effective semantic space relating action classes remains challenging. We address this by introducing a novel dataset, Stories, which contains rich textual descriptions for diverse action classes extracted from WikiHow articles. For each class, we extract multi-sentence narratives detailing the necessary steps, scenes, objects, and verbs that characterize the action. This contextual data enables modeling of nuanced relationships between actions, paving the way for zero-shot transfer. We also propose an approach that harnesses Stories to improve feature generation for training zero-shot classification. Without any target dataset fine-tuning, our method achieves new state-of-the-art on multiple benchmarks, improving top-1 accuracy by up to 6.1%. We believe Stories provides a valuable resource that can catalyze progress in zero-shot action recognition. The textual narratives forge connections between seen and unseen classes, overcoming the bottleneck of labeled data that has long impeded advancements in this exciting domain. The data can be found here: https://github.com/kini5gowda/Stories .

Learning Action Changes by Measuring Verb-Adverb Textual Relationships

The goal of this work is to understand the way actions are performed in videos. That is, given a video, we aim to predict an adverb indicating a modification applied to the action (e.g. cut "finely"). We cast this problem as a regression task. We measure textual relationships between verbs and adverbs to generate a regression target representing the action change we aim to learn. We test our approach on a range of datasets and achieve state-of-the-art results on both adverb prediction and antonym classification. Furthermore, we outperform previous work when we lift two commonly assumed conditions: the availability of action labels during testing and the pairing of adverbs as antonyms. Existing datasets for adverb recognition are either noisy, which makes learning difficult, or contain actions whose appearance is not influenced by adverbs, which makes evaluation less reliable. To address this, we collect a new high quality dataset: Adverbs in Recipes (AIR). We focus on instructional recipes videos, curating a set of actions that exhibit meaningful visual changes when performed differently. Videos in AIR are more tightly trimmed and were manually reviewed by multiple annotators to ensure high labelling quality. Results show that models learn better from AIR given its cleaner videos. At the same time, adverb prediction on AIR is challenging, demonstrating that there is considerable room for improvement.

LOCATE: Localize and Transfer Object Parts for Weakly Supervised Affordance Grounding

Humans excel at acquiring knowledge through observation. For example, we can learn to use new tools by watching demonstrations. This skill is fundamental for intelligent systems to interact with the world. A key step to acquire this skill is to identify what part of the object affords each action, which is called affordance grounding. In this paper, we address this problem and propose a framework called LOCATE that can identify matching object parts across images, to transfer knowledge from images where an object is being used (exocentric images used for learning), to images where the object is inactive (egocentric ones used to test). To this end, we first find interaction areas and extract their feature embeddings. Then we learn to aggregate the embeddings into compact prototypes (human, object part, and background), and select the one representing the object part. Finally, we use the selected prototype to guide affordance grounding. We do this in a weakly supervised manner, learning only from image-level affordance and object labels. Extensive experiments demonstrate that our approach outperforms state-of-the-art methods by a large margin on both seen and unseen objects.