David Ross

Shen Yan, Xuehan Xiong, Arsha Nagrani et al.

While large-scale image-text pretrained models such as CLIP have been used for multiple video-level tasks on trimmed videos, their use for temporal localization in untrimmed videos is still a relatively unexplored task. We design a new approach for this called UnLoc, which uses pretrained image and text towers, and feeds tokens to a video-text fusion model. The output of the fusion module are then used to construct a feature pyramid in which each level connects to a head to predict a per-frame relevancy score and start/end time displacements. Unlike previous works, our architecture enables Moment Retrieval, Temporal Localization, and Action Segmentation with a single stage model, without the need for action proposals, motion based pretrained features or representation masking. Unlike specialized models, we achieve state of the art results on all three different localization tasks with a unified approach. Code will be available at: \url{https://github.com/google-research/scenic}.

Lu Mi, Abhijit Kundu, David Ross et al. · deepmind

We propose im2nerf, a learning framework that predicts a continuous neural object representation given a single input image in the wild, supervised by only segmentation output from off-the-shelf recognition methods. The standard approach to constructing neural radiance fields takes advantage of multi-view consistency and requires many calibrated views of a scene, a requirement that cannot be satisfied when learning on large-scale image data in the wild. We take a step towards addressing this shortcoming by introducing a model that encodes the input image into a disentangled object representation that contains a code for object shape, a code for object appearance, and an estimated camera pose from which the object image is captured. Our model conditions a NeRF on the predicted object representation and uses volume rendering to generate images from novel views. We train the model end-to-end on a large collection of input images. As the model is only provided with single-view images, the problem is highly under-constrained. Therefore, in addition to using a reconstruction loss on the synthesized input view, we use an auxiliary adversarial loss on the novel rendered views. Furthermore, we leverage object symmetry and cycle camera pose consistency. We conduct extensive quantitative and qualitative experiments on the ShapeNet dataset as well as qualitative experiments on Open Images dataset. We show that in all cases, im2nerf achieves the state-of-the-art performance for novel view synthesis from a single-view unposed image in the wild.

Gheorghe Comanici, Eric Bieber, Mike Schaekermann et al. · amazon-science, baidu

In this report, we introduce the Gemini 2.X model family: Gemini 2.5 Pro and Gemini 2.5 Flash, as well as our earlier Gemini 2.0 Flash and Flash-Lite models. Gemini 2.5 Pro is our most capable model yet, achieving SoTA performance on frontier coding and reasoning benchmarks. In addition to its incredible coding and reasoning skills, Gemini 2.5 Pro is a thinking model that excels at multimodal understanding and it is now able to process up to 3 hours of video content. Its unique combination of long context, multimodal and reasoning capabilities can be combined to unlock new agentic workflows. Gemini 2.5 Flash provides excellent reasoning abilities at a fraction of the compute and latency requirements and Gemini 2.0 Flash and Flash-Lite provide high performance at low latency and cost. Taken together, the Gemini 2.X model generation spans the full Pareto frontier of model capability vs cost, allowing users to explore the boundaries of what is possible with complex agentic problem solving.

Townim Faisal Chowdhury, Kewen Liao, Vu Minh Hieu Phan et al.

Deep Neural Networks (DNNs) are widely used for visual classification tasks, but their complex computation process and black-box nature hinder decision transparency and interpretability. Class activation maps (CAMs) and recent variants provide ways to visually explain the DNN decision-making process by displaying 'attention' heatmaps of the DNNs. Nevertheless, the CAM explanation only offers relative attention information, that is, on an attention heatmap, we can interpret which image region is more or less important than the others. However, these regions cannot be meaningfully compared across classes, and the contribution of each region to the model's class prediction is not revealed. To address these challenges that ultimately lead to better DNN Interpretation, in this paper, we propose CAPE, a novel reformulation of CAM that provides a unified and probabilistically meaningful assessment of the contributions of image regions. We quantitatively and qualitatively compare CAPE with state-of-the-art CAM methods on CUB and ImageNet benchmark datasets to demonstrate enhanced interpretability. We also test on a cytology imaging dataset depicting a challenging Chronic Myelomonocytic Leukemia (CMML) diagnosis problem. Code is available at: https://github.com/AIML-MED/CAPE.

Jasper Uijlings, Xingyi Zhou, Xiuye Gu et al.

Understanding objects in videos in terms of fine-grained localization masks and detailed semantic properties is a fundamental task in video understanding. In this paper, we propose VoCap, a flexible video model that consumes a video and a prompt of various modalities (text, box or mask), and produces a spatio-temporal masklet with a corresponding object-centric caption. As such our model addresses simultaneously the tasks of promptable video object segmentation, referring expression segmentation, and object captioning. Since obtaining data for this task is tedious and expensive, we propose to annotate an existing large-scale segmentation dataset (SAV) with pseudo object captions. We do so by preprocessing videos with their ground-truth masks to highlight the object of interest and feed this to a large Vision Language Model (VLM). For an unbiased evaluation, we collect manual annotations on the validation set. We call the resulting dataset SAV-Caption. We train our VoCap model at scale on a SAV-Caption together with a mix of other image and video datasets. Our model yields state-of-the-art results on referring expression video object segmentation, is competitive on semi-supervised video object segmentation, and establishes a benchmark for video object captioning. Our dataset will be made available at https://github.com/google-deepmind/vocap.

Sihyun Yu, Meera Hahn, Dan Kondratyuk et al.

Diffusion models are successful for synthesizing high-quality videos but are limited to generating short clips (e.g., 2-10 seconds). Synthesizing sustained footage (e.g. over minutes) still remains an open research question. In this paper, we propose MALT Diffusion (using Memory-Augmented Latent Transformers), a new diffusion model specialized for long video generation. MALT Diffusion (or just MALT) handles long videos by subdividing them into short segments and doing segment-level autoregressive generation. To achieve this, we first propose recurrent attention layers that encode multiple segments into a compact memory latent vector; by maintaining this memory vector over time, MALT is able to condition on it and continuously generate new footage based on a long temporal context. We also present several training techniques that enable the model to generate frames over a long horizon with consistent quality and minimal degradation. We validate the effectiveness of MALT through experiments on long video benchmarks. We first perform extensive analysis of MALT in long-contextual understanding capability and stability using popular long video benchmarks. For example, MALT achieves an FVD score of 220.4 on 128-frame video generation on UCF-101, outperforming the previous state-of-the-art of 648.4. Finally, we explore MALT's capabilities in a text-to-video generation setting and show that it can produce long videos compared with recent techniques for long text-to-video generation.

Bo Hu, Bryan Seybold, Shan Yang et al.

We present a method to infer the 3D pose of mice, including the limbs and feet, from monocular videos. Many human clinical conditions and their corresponding animal models result in abnormal motion, and accurately measuring 3D motion at scale offers insights into health. The 3D poses improve classification of health-related attributes over 2D representations. The inferred poses are accurate enough to estimate stride length even when the feet are mostly occluded. This method could be applied as part of a continuous monitoring system to non-invasively measure animal health.

Abhijit Kundu, Xiaoqi Yin, Alireza Fathi et al.

Semantic segmentation of 3D meshes is an important problem for 3D scene understanding. In this paper we revisit the classic multiview representation of 3D meshes and study several techniques that make them effective for 3D semantic segmentation of meshes. Given a 3D mesh reconstructed from RGBD sensors, our method effectively chooses different virtual views of the 3D mesh and renders multiple 2D channels for training an effective 2D semantic segmentation model. Features from multiple per view predictions are finally fused on 3D mesh vertices to predict mesh semantic segmentation labels. Using the large scale indoor 3D semantic segmentation benchmark of ScanNet, we show that our virtual views enable more effective training of 2D semantic segmentation networks than previous multiview approaches. When the 2D per pixel predictions are aggregated on 3D surfaces, our virtual multiview fusion method is able to achieve significantly better 3D semantic segmentation results compared to all prior multiview approaches and competitive with recent 3D convolution approaches.

Yue Wang, Alireza Fathi, Abhijit Kundu et al.

We present a simple and flexible object detection framework optimized for autonomous driving. Building on the observation that point clouds in this application are extremely sparse, we propose a practical pillar-based approach to fix the imbalance issue caused by anchors. In particular, our algorithm incorporates a cylindrical projection into multi-view feature learning, predicts bounding box parameters per pillar rather than per point or per anchor, and includes an aligned pillar-to-point projection module to improve the final prediction. Our anchor-free approach avoids hyperparameter search associated with past methods, simplifying 3D object detection while significantly improving upon state-of-the-art.

Mahyar Najibi, Guangda Lai, Abhijit Kundu et al.

We propose DOPS, a fast single-stage 3D object detection method for LIDAR data. Previous methods often make domain-specific design decisions, for example projecting points into a bird-eye view image in autonomous driving scenarios. In contrast, we propose a general-purpose method that works on both indoor and outdoor scenes. The core novelty of our method is a fast, single-pass architecture that both detects objects in 3D and estimates their shapes. 3D bounding box parameters are estimated in one pass for every point, aggregated through graph convolutions, and fed into a branch of the network that predicts latent codes representing the shape of each detected object. The latent shape space and shape decoder are learned on a synthetic dataset and then used as supervision for the end-to-end training of the 3D object detection pipeline. Thus our model is able to extract shapes without access to ground-truth shape information in the target dataset. During experiments, we find that our proposed method achieves state-of-the-art results by ~5% on object detection in ScanNet scenes, and it gets top results by 3.4% in the Waymo Open Dataset, while reproducing the shapes of detected cars.

Arsha Nagrani, Chen Sun, David Ross et al.

Is it possible to guess human action from dialogue alone? In this work we investigate the link between spoken words and actions in movies. We note that movie screenplays describe actions, as well as contain the speech of characters and hence can be used to learn this correlation with no additional supervision. We train a BERT-based Speech2Action classifier on over a thousand movie screenplays, to predict action labels from transcribed speech segments. We then apply this model to the speech segments of a large unlabelled movie corpus (188M speech segments from 288K movies). Using the predictions of this model, we obtain weak action labels for over 800K video clips. By training on these video clips, we demonstrate superior action recognition performance on standard action recognition benchmarks, without using a single manually labelled action example.