Scaling 4D Representations

Scaling has not yet been convincingly demonstrated for pure self-supervised learning from video. However, prior work has focused evaluations on semantic-related tasks $\unicode{x2013}$ action classification, ImageNet classification, etc. In this paper we focus on evaluating self-supervised learning on non-semantic vision tasks that are more spatial (3D) and temporal (+1D = 4D), such as camera pose estimation, point and object tracking, and depth estimation. We show that by learning from very large video datasets, masked auto-encoding (MAE) with transformer video models actually scales, consistently improving performance on these 4D tasks, as model size increases from 20M all the way to the largest by far reported self-supervised video model $\unicode{x2013}$ 22B parameters. Rigorous apples-to-apples comparison with many recent image and video models demonstrates the benefits of scaling 4D representations.

TRecViT: A Recurrent Video Transformer

We propose a novel block for video modelling. It relies on a time-space-channel factorisation with dedicated blocks for each dimension: gated linear recurrent units (LRUs) perform information mixing over time, self-attention layers perform mixing over space, and MLPs over channels. The resulting architecture TRecViT performs well on sparse and dense tasks, trained in supervised or self-supervised regimes. Notably, our model is causal and outperforms or is on par with a pure attention model ViViT-L on large scale video datasets (SSv2, Kinetics400), while having $3\times$ less parameters, $12\times$ smaller memory footprint, and $5\times$ lower FLOPs count. Code and checkpoints will be made available online at https://github.com/google-deepmind/trecvit.

Revisiting Text-to-Image Evaluation with Gecko: On Metrics, Prompts, and Human Ratings

While text-to-image (T2I) generative models have become ubiquitous, they do not necessarily generate images that align with a given prompt. While previous work has evaluated T2I alignment by proposing metrics, benchmarks, and templates for collecting human judgements, the quality of these components is not systematically measured. Human-rated prompt sets are generally small and the reliability of the ratings -- and thereby the prompt set used to compare models -- is not evaluated. We address this gap by performing an extensive study evaluating auto-eval metrics and human templates. We provide three main contributions: (1) We introduce a comprehensive skills-based benchmark that can discriminate models across different human templates. This skills-based benchmark categorises prompts into sub-skills, allowing a practitioner to pinpoint not only which skills are challenging, but at what level of complexity a skill becomes challenging. (2) We gather human ratings across four templates and four T2I models for a total of >100K annotations. This allows us to understand where differences arise due to inherent ambiguity in the prompt and where they arise due to differences in metric and model quality. (3) Finally, we introduce a new QA-based auto-eval metric that is better correlated with human ratings than existing metrics for our new dataset, across different human templates, and on TIFA160.

NiSNN-A: Non-iterative Spiking Neural Networks with Attention with Application to Motor Imagery EEG Classification

Motor imagery, an important category in electroencephalogram (EEG) research, often intersects with scenarios demanding low energy consumption, such as portable medical devices and isolated environment operations. Traditional deep learning algorithms, despite their effectiveness, are characterized by significant computational demands accompanied by high energy usage. As an alternative, spiking neural networks (SNNs), inspired by the biological functions of the brain, emerge as a promising energy-efficient solution. However, SNNs typically exhibit lower accuracy than their counterpart convolutional neural networks (CNNs). Although attention mechanisms successfully increase network accuracy by focusing on relevant features, their integration in the SNN framework remains an open question. In this work, we combine the SNN and the attention mechanisms for the EEG classification, aiming to improve precision and reduce energy consumption. To this end, we first propose a Non-iterative Leaky Integrate-and-Fire (LIF) neuron model, overcoming the gradient issues in the traditional SNNs using the Iterative LIF neurons. Then, we introduce the sequence-based attention mechanisms to refine the feature map. We evaluated the proposed Non-iterative SNN with Attention (NiSNN-A) model on OpenBMI, a large-scale motor imagery dataset. Experiment results demonstrate that 1) our model outperforms other SNN models by achieving higher accuracy, 2) our model increases energy efficiency compared to the counterpart CNN models (i.e., by 2.27 times) while maintaining comparable accuracy.

Helping Hands: An Object-Aware Ego-Centric Video Recognition Model

We introduce an object-aware decoder for improving the performance of spatio-temporal representations on ego-centric videos. The key idea is to enhance object-awareness during training by tasking the model to predict hand positions, object positions, and the semantic label of the objects using paired captions when available. At inference time the model only requires RGB frames as inputs, and is able to track and ground objects (although it has not been trained explicitly for this). We demonstrate the performance of the object-aware representations learnt by our model, by: (i) evaluating it for strong transfer, i.e. through zero-shot testing, on a number of downstream video-text retrieval and classification benchmarks; and (ii) by using the representations learned as input for long-term video understanding tasks (e.g. Episodic Memory in Ego4D). In all cases the performance improves over the state of the art -- even compared to networks trained with far larger batch sizes. We also show that by using noisy image-level detection as pseudo-labels in training, the model learns to provide better bounding boxes using video consistency, as well as grounding the words in the associated text descriptions. Overall, we show that the model can act as a drop-in replacement for an ego-centric video model to improve performance through visual-text grounding.

Making the Most of What You Have: Adapting Pre-trained Visual Language Models in the Low-data Regime

Large-scale visual language models are widely used as pre-trained models and then adapted for various downstream tasks. While humans are known to efficiently learn new tasks from a few examples, deep learning models struggle with adaptation from few examples. In this work, we look into task adaptation in the low-data regime, and provide a thorough study of the existing adaptation methods for generative Visual Language Models. And we show important benefits of self-labelling, i.e. using the model's own predictions to self-improve when having access to a larger number of unlabelled images of the same distribution. Our study demonstrates significant gains using our proposed task adaptation pipeline across a wide range of visual language tasks such as visual classification (ImageNet), visual captioning (COCO), detailed visual captioning (Localised Narratives) and visual question answering (VQAv2).

Is an Object-Centric Video Representation Beneficial for Transfer?

The objective of this work is to learn an object-centric video representation, with the aim of improving transferability to novel tasks, i.e., tasks different from the pre-training task of action classification. To this end, we introduce a new object-centric video recognition model based on a transformer architecture. The model learns a set of object-centric summary vectors for the video, and uses these vectors to fuse the visual and spatio-temporal trajectory `modalities' of the video clip. We also introduce a novel trajectory contrast loss to further enhance objectness in these summary vectors. With experiments on four datasets -- SomethingSomething-V2, SomethingElse, Action Genome and EpicKitchens -- we show that the object-centric model outperforms prior video representations (both object-agnostic and object-aware), when: (1) classifying actions on unseen objects and unseen environments; (2) low-shot learning to novel classes; (3) linear probe to other downstream tasks; as well as (4) for standard action classification.

Temporal Query Networks for Fine-grained Video Understanding

Our objective in this work is fine-grained classification of actions in untrimmed videos, where the actions may be temporally extended or may span only a few frames of the video. We cast this into a query-response mechanism, where each query addresses a particular question, and has its own response label set. We make the following four contributions: (I) We propose a new model - a Temporal Query Network - which enables the query-response functionality, and a structural understanding of fine-grained actions. It attends to relevant segments for each query with a temporal attention mechanism, and can be trained using only the labels for each query. (ii) We propose a new way - stochastic feature bank update - to train a network on videos of various lengths with the dense sampling required to respond to fine-grained queries. (iii) We compare the TQN to other architectures and text supervision methods, and analyze their pros and cons. Finally, (iv) we evaluate the method extensively on the FineGym and Diving48 benchmarks for fine-grained action classification and surpass the state-of-the-art using only RGB features.

Adaptive Text Recognition through Visual Matching

In this work, our objective is to address the problems of generalization and flexibility for text recognition in documents. We introduce a new model that exploits the repetitive nature of characters in languages, and decouples the visual representation learning and linguistic modelling stages. By doing this, we turn text recognition into a shape matching problem, and thereby achieve generalization in appearance and flexibility in classes. We evaluate the new model on both synthetic and real datasets across different alphabets and show that it can handle challenges that traditional architectures are not able to solve without expensive retraining, including: (i) it can generalize to unseen fonts without new exemplars from them; (ii) it can flexibly change the number of classes, simply by changing the exemplars provided; and (iii) it can generalize to new languages and new characters that it has not been trained for by providing a new glyph set. We show significant improvements over state-of-the-art models for all these cases.