Publications (14)
Virtual Multi-view Fusion for 3D Semantic Segmentation
Abhijit Kundu, Xiaoqi Yin, Alireza Fathi +4
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…
First results of the SOAP project. Open access publishing in 2010
Suenje Dallmeier-Tiessen, Robert Darby, Bettina Goerner +13
The SOAP (Study of Open Access Publishing) project has compiled data on the present offer for open access publishing in online peer-reviewed journals. Starting from the Directory o…
MALT Diffusion: Memory-Augmented Latent Transformers for Any-Length Video Generation
Sihyun Yu, Meera Hahn, Dan Kondratyuk +6
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 minut…
UnLoc: A Unified Framework for Video Localization Tasks
Shen Yan, Xuehan Xiong, Arsha Nagrani +5
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…
VoCap: Video Object Captioning and Segmentation from Any Prompt
Jasper Uijlings, Xingyi Zhou, Xiuye Gu +5
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…
Advantages of multistage quantum walks over QAOA
Lasse Gerblich, Tamanna Dasanjh, Horatio Q. X. Wong +4
Methods to find the solution state for optimization problems encoded into Ising Hamiltonians are a very active area of current research. In this work we compare the quantum approxi…
Pillar-based Object Detection for Autonomous Driving
Yue Wang, Alireza Fathi, Abhijit Kundu +4
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…
DOPS: Learning to Detect 3D Objects and Predict their 3D Shapes
Mahyar Najibi, Guangda Lai, Abhijit Kundu +7
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 b…
Highlights from the SOAP project survey. What Scientists Think about Open Access Publishing
Suenje Dallmeier-Tiessen, Robert Darby, Bettina Goerner +14
The SOAP (Study of Open Access Publishing) project has run a large-scale survey of the attitudes of researchers on, and the experiences with, open access publishing. Around forty t…
CAPE: CAM as a Probabilistic Ensemble for Enhanced DNN Interpretation
Townim Faisal Chowdhury, Kewen Liao, Vu Minh Hieu Phan +7
Deep Neural Networks (DNNs) are widely used for visual classification tasks, but their complex computation process and black-box nature hinder decision transparency and interpretab…
im2nerf: Image to Neural Radiance Field in the Wild
Lu Mi, Abhijit Kundu, David Ross +3
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…
Speech2Action: Cross-modal Supervision for Action Recognition
Arsha Nagrani, Chen Sun, David Ross +3
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 a…
Optical Mouse: 3D Mouse Pose From Single-View Video
Bo Hu, Bryan Seybold, Shan Yang +4
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 i…
Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities
Gheorghe Comanici, Eric Bieber, Mike Schaekermann +3431
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…