Chuhan Zhang

Letian Wang, Chuhan Zhang, Rishabh Kabra et al.

Driven by next-token prediction, NLP shifted from task-specific models into powerful generalist foundation models. What, then, is the equivalent catalyst needed to achieve a general-purpose model in computer vision? In this paper, we contend that large-scale text-to-video generation serves as a strong pre-training paradigm for computer vision, providing the necessary spatiotemporal priors, vision-language alignment, and scalability required for general visual intelligence. We introduce GenCeption, which leverages a pre-trained video generative diffusion backbone to define a feed-forward perception model, capable of performing various vision tasks steered by text instructions. Empirical results demonstrate that GenCeption achieves state-of-the-art performance across a diverse suite of tasks, including depth, surface normal, and camera pose estimation, expression-referring segmentation, and 3D keypoint prediction, often matching or surpassing specialized models (e.g. DepthAnything3, SAM3, D4RT, VGGT-Omega, Sapiens, David, Genmo, and Lotus-2). Furthermore, the video generative pretrained backbone outperforms alternative pretraining paradigms (e.g., V-JEPA, and Video MAE) under comparable settings. Importantly, GenCeption exhibits preliminary data and model scaling properties along with exceptional data efficiency, where it achieves comparable performance with leading models like D4RT and VGGT-Omega with 7 to 500 less training data. Finally, GenCeption also exhibits intriguing emergent behaviors: a model trained exclusively on synthetic human videos generalizes to real-world footage and out-of-distribution object categories (e.g., animals and robots). These findings suggest that video generation is not merely a synthesis tool, but a foundational path toward generalist vision intelligence for the physical world. Project page: https://genception.github.io

Chuhan Zhang, Ankush Gupta, Andrew Zisserman

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 of novel classes; (3) linear probe to other downstream tasks; as well as (4) for standard action classification.

Chuhan Zhang, Ankush Gupta, Andrew Zisserman

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.

João Carreira, Dilara Gokay, Michael King et al.

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. Pretrained models are available at https://github.com/google-deepmind/representations4d .

Viorica Pătrăucean, Xu Owen He, Joseph Heyward et al. · deepmind

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.

Lin Li, Chuhan Zhang, Dong Zhang et al.

Open-vocabulary scene graph generation (OVSGG) extends traditional SGG by recognizing novel objects and relationships beyond predefined categories, leveraging the knowledge from pre-trained large-scale models. Existing OVSGG methods always adopt a two-stage pipeline: 1) \textit{Infusing knowledge} into large-scale models via pre-training on large datasets; 2) \textit{Transferring knowledge} from pre-trained models with fully annotated scene graphs during supervised fine-tuning. However, due to a lack of explicit interaction modeling, these methods struggle to distinguish between interacting and non-interacting instances of the same object category. This limitation induces critical issues in both stages of OVSGG: it generates noisy pseudo-supervision from mismatched objects during knowledge infusion, and causes ambiguous query matching during knowledge transfer. To this end, in this paper, we propose an inter\textbf{AC}tion-\textbf{C}entric end-to-end OVSGG framework (\textbf{ACC}) in an interaction-driven paradigm to minimize these mismatches. For \textit{interaction-centric knowledge infusion}, ACC employs a bidirectional interaction prompt for robust pseudo-supervision generation to enhance the model's interaction knowledge. For \textit{interaction-centric knowledge transfer}, ACC first adopts interaction-guided query selection that prioritizes pairing interacting objects to reduce interference from non-interacting ones. Then, it integrates interaction-consistent knowledge distillation to bolster robustness by pushing relational foreground away from the background while retaining general knowledge. Extensive experimental results on three benchmarks show that ACC achieves state-of-the-art performance, demonstrating the potential of interaction-centric paradigms for real-world applications.

Chuhan Zhang, Chaoyang Zhu, Pingcheng Dong et al.

In pursuit of detecting unstinted objects that extend beyond predefined categories, prior arts of open-vocabulary object detection (OVD) typically resort to pretrained vision-language models (VLMs) for base-to-novel category generalization. However, to mitigate the misalignment between upstream image-text pretraining and downstream region-level perception, additional supervisions are indispensable, eg, image-text pairs or pseudo annotations generated via self-training strategies. In this work, we propose CCKT-Det trained without any extra supervision. The proposed framework constructs a cyclic and dynamic knowledge transfer from language queries and visual region features extracted from VLMs, which forces the detector to closely align with the visual-semantic space of VLMs. Specifically, 1) we prefilter and inject semantic priors to guide the learning of queries, and 2) introduce a regional contrastive loss to improve the awareness of queries on novel objects. CCKT-Det can consistently improve performance as the scale of VLMs increases, all while requiring the detector at a moderate level of computation overhead. Comprehensive experimental results demonstrate that our method achieves performance gain of +2.9% and +10.2% AP50 over previous state-of-the-arts on the challenging COCO benchmark, both without and with a stronger teacher model.

Chuhan Zhang, Cong Wang, Wei Pan et al.

Inspired by the dynamic coupling of moto-neurons and physical elasticity in animals, this work explores the possibility of generating locomotion gaits by utilizing physical oscillations in a soft snake by means of a low-level spiking neural mechanism. To achieve this goal, we introduce the Double Threshold Spiking neuron model with adjustable thresholds to generate varied output patterns. This neuron model can excite the natural dynamics of soft robotic snakes, and it enables distinct movements, such as turning or moving forward, by simply altering the neural thresholds. Finally, we demonstrate that our approach, termed SpikingSoft, naturally pairs and integrates with reinforcement learning. The high-level agent only needs to adjust the two thresholds to generate complex movement patterns, thus strongly simplifying the learning of reactive locomotion. Simulation results demonstrate that the proposed architecture significantly enhances the performance of the soft snake robot, enabling it to achieve target objectives with a 21.6% increase in success rate, a 29% reduction in time to reach the target, and smoother movements compared to the vanilla reinforcement learning controllers or Central Pattern Generator controller acting in torque space.

Chuhan Zhang, Wei Pan, Cosimo Della Santina

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.

Lin Li, Chuhan Zhang, Dong Zhang et al.

Today's open vocabulary scene graph generation (OVSGG) extends traditional SGG by recognizing novel objects and relationships beyond predefined categories, leveraging the knowledge from pre-trained large-scale models. Most existing methods adopt a two-stage pipeline: weakly supervised pre-training with image captions and supervised fine-tuning (SFT) on fully annotated scene graphs. Nonetheless, they omit explicit modeling of interacting objects and treat all objects equally, resulting in mismatched relation pairs. To this end, we propose an interaction-aware OVSGG framework INOVA. During pre-training, INOVA employs an interaction-aware target generation strategy to distinguish interacting objects from non-interacting ones. In SFT, INOVA devises an interaction-guided query selection tactic to prioritize interacting objects during bipartite graph matching. Besides, INOVA is equipped with an interaction-consistent knowledge distillation to enhance the robustness by pushing interacting object pairs away from the background. Extensive experiments on two benchmarks (VG and GQA) show that INOVA achieves state-of-the-art performance, demonstrating the potential of interaction-aware mechanisms for real-world applications.

Yuan Tian, Chuhan Zhang, Xiaotong Wang et al.

Creating data reports is a labor-intensive task involving iterative data exploration, insight extraction, and narrative construction. A key challenge lies in composing the analysis logic-from defining objectives and transforming data to identifying and communicating insights. Manually crafting this logic can be cognitively demanding. While experienced analysts often reuse scripts from past projects, finding a perfect match for a new dataset is rare. Even when similar analyses are available online, they usually share only results or visualizations, not the underlying code, making reuse difficult. To address this, we present ReSpark, a system that leverages large language models (LLMs) to reverse-engineer analysis logic from existing reports and adapt it to new datasets. By generating draft analysis steps, ReSpark provides a warm start for users. It also supports interactive refinement, allowing users to inspect intermediate outputs, insert objectives, and revise content. We evaluate ReSpark through comparative and user studies, demonstrating its effectiveness in lowering the barrier to generating data reports without relying on existing analysis code.

Chuhan Zhang, Antoine Miech, Jiajun Shen et al.

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).

Chuhan Zhang, Ankush Gupta, Andrew Zisserman

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.

Chuhan Zhang, Ankush Gupta, Andrew Zisserman

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.