papers

Publications (40)

cs.MM2022

It's Time for Artistic Correspondence in Music and Video

Didac Suris, Carl Vondrick, Bryan Russell +1

We present an approach for recommending a music track for a given video, and vice versa, based on both their temporal alignment and their correspondence at an artistic level. We pr…

cs.CV2025

ResidualViT for Efficient Temporally Dense Video Encoding

Mattia Soldan, Fabian Caba Heilbron, Bernard Ghanem +2

Several video understanding tasks, such as natural language temporal video grounding, temporal activity localization, and audio description generation, require "temporally dense" r…

cs.CV2019

FreiHAND: A Dataset for Markerless Capture of Hand Pose and Shape from Single RGB Images

Christian Zimmermann, Duygu Ceylan, Jimei Yang +3

Estimating 3D hand pose from single RGB images is a highly ambiguous problem that relies on an unbiased training dataset. In this paper, we analyze cross-dataset generalization whe…

cs.CV2022

Finding Moments in Video Collections Using Natural Language

Victor Escorcia, Mattia Soldan, Josef Sivic +2

We introduce the task of retrieving relevant video moments from a large corpus of untrimmed, unsegmented videos given a natural language query. Our task poses unique challenges as…

cs.CV2024

Adapting Dual-encoder Vision-language Models for Paraphrased Retrieval

Jiacheng Cheng, Hijung Valentina Shin, Nuno Vasconcelos +2

In the recent years, the dual-encoder vision-language models (\eg CLIP) have achieved remarkable text-to-image retrieval performance. However, we discover that these models usually…

cs.CV2021

Look at What I'm Doing: Self-Supervised Spatial Grounding of Narrations in Instructional Videos

Reuben Tan, Bryan A. Plummer, Kate Saenko +2

We introduce the task of spatially localizing narrated interactions in videos. Key to our approach is the ability to learn to spatially localize interactions with self-supervision…

cs.CV2021

Editing Conditional Radiance Fields

Steven Liu, Xiuming Zhang, Zhoutong Zhang +3

A neural radiance field (NeRF) is a scene model supporting high-quality view synthesis, optimized per scene. In this paper, we explore enabling user editing of a category-level NeR…

cs.CV2024

Generative Timelines for Instructed Visual Assembly

Alejandro Pardo, Jui-Hsien Wang, Bernard Ghanem +3

The objective of this work is to manipulate visual timelines (e.g. a video) through natural language instructions, making complex timeline editing tasks accessible to non-expert or…

cs.CV2022

Focal Length and Object Pose Estimation via Render and Compare

Georgy Ponimatkin, Yann Labbé, Bryan Russell +2

We introduce FocalPose, a neural render-and-compare method for jointly estimating the camera-object 6D pose and camera focal length given a single RGB input image depicting a known…

cs.CV2024

NewMove: Customizing text-to-video models with novel motions

Joanna Materzynska, Josef Sivic, Eli Shechtman +3

We introduce an approach for augmenting text-to-video generation models with customized motions, extending their capabilities beyond the motions depicted in the original training d…

cs.CV2021

Contrastive Feature Loss for Image Prediction

Alex Andonian, Taesung Park, Bryan Russell +3

Training supervised image synthesis models requires a critic to compare two images: the ground truth to the result. Yet, this basic functionality remains an open problem. A popular…

cs.CV2021

Weakly Supervised Human-Object Interaction Detection in Video via Contrastive Spatiotemporal Regions

Shuang Li, Yilun Du, Antonio Torralba +2

We introduce the task of weakly supervised learning for detecting human and object interactions in videos. Our task poses unique challenges as a system does not know what types of…

cs.CV2017

ActionVLAD: Learning spatio-temporal aggregation for action classification

Rohit Girdhar, Deva Ramanan, Abhinav Gupta +2

In this work, we introduce a new video representation for action classification that aggregates local convolutional features across the entire spatio-temporal extent of the video.…

cs.CV2023

Meta-Personalizing Vision-Language Models to Find Named Instances in Video

Chun-Hsiao Yeh, Bryan Russell, Josef Sivic +2

Large-scale vision-language models (VLM) have shown impressive results for language-guided search applications. While these models allow category-level queries, they currently stru…

cs.CV2023

Language-Guided Music Recommendation for Video via Prompt Analogies

Daniel McKee, Justin Salamon, Josef Sivic +1

We propose a method to recommend music for an input video while allowing a user to guide music selection with free-form natural language. A key challenge of this problem setting is…

cs.CV2025

Improving Personalized Search with Regularized Low-Rank Parameter Updates

Fiona Ryan, Josef Sivic, Fabian Caba Heilbron +3

Personalized vision-language retrieval seeks to recognize new concepts (e.g. "my dog Fido") from only a few examples. This task is challenging because it requires not only learning…

cs.CV2016

Deep Exemplar 2D-3D Detection by Adapting from Real to Rendered Views

Francisco Massa, Bryan Russell, Mathieu Aubry

This paper presents an end-to-end convolutional neural network (CNN) for 2D-3D exemplar detection. We demonstrate that the ability to adapt the features of natural images to better…

cs.HC2017

Learning Visual Importance for Graphic Designs and Data Visualizations

Zoya Bylinskii, Nam Wook Kim, Peter O'Donovan +6

Knowing where people look and click on visual designs can provide clues about how the designs are perceived, and where the most important or relevant content lies. The most importa…

cs.CV2022

Neural Volumetric Object Selection

Zhongzheng Ren, Aseem Agarwala, Bryan Russell +2

We introduce an approach for selecting objects in neural volumetric 3D representations, such as multi-plane images (MPI) and neural radiance fields (NeRF). Our approach takes a set…

cs.CV2018

Localizing Moments in Video with Temporal Language

Lisa Anne Hendricks, Oliver Wang, Eli Shechtman +3

Localizing moments in a longer video via natural language queries is a new, challenging task at the intersection of language and video understanding. Though moment localization wit…

cs.CV2016

PixelNet: Towards a General Pixel-level Architecture

Aayush Bansal, Xinlei Chen, Bryan Russell +2

We explore architectures for general pixel-level prediction problems, from low-level edge detection to mid-level surface normal estimation to high-level semantic segmentation. Conv…

cs.CV2023

Language-Guided Audio-Visual Source Separation via Trimodal Consistency

Reuben Tan, Arijit Ray, Andrea Burns +5

We propose a self-supervised approach for learning to perform audio source separation in videos based on natural language queries, using only unlabeled video and audio pairs as tra…

cs.CV2025

EditDuet: A Multi-Agent System for Video Non-Linear Editing

Marcelo Sandoval-Castaneda, Bryan Russell, Josef Sivic +2

Automated tools for video editing and assembly have applications ranging from filmmaking and advertisement to content creation for social media. Previous video editing work has mai…

cs.HC2019

B-Script: Transcript-based B-roll Video Editing with Recommendations

Bernd Huber, Hijung Valentina Shin, Bryan Russell +2

In video production, inserting B-roll is a widely used technique to enrich the story and make a video more engaging. However, determining the right content and positions of B-roll…

cs.CV2022

Monocular Dynamic View Synthesis: A Reality Check

Hang Gao, Ruilong Li, Shubham Tulsiani +2

We study the recent progress on dynamic view synthesis (DVS) from monocular video. Though existing approaches have demonstrated impressive results, we show a discrepancy between th…

cs.CV2019

Bounce and Learn: Modeling Scene Dynamics with Real-World Bounces

Senthil Purushwalkam, Abhinav Gupta, Danny M. Kaufman +1

We introduce an approach to model surface properties governing bounces in everyday scenes. Our model learns end-to-end, starting from sensor inputs, to predict post-bounce trajecto…

cs.CV2024

FocalPose++: Focal Length and Object Pose Estimation via Render and Compare

Martin Cífka, Georgy Ponimatkin, Yann Labbé +4

We introduce FocalPose++, a neural render-and-compare method for jointly estimating the camera-object 6D pose and camera focal length given a single RGB input image depicting a kno…

cs.CV2024

Koala: Key frame-conditioned long video-LLM

Reuben Tan, Ximeng Sun, Ping Hu +5

Long video question answering is a challenging task that involves recognizing short-term activities and reasoning about their fine-grained relationships. State-of-the-art video Lar…

cs.CV2016

Marr Revisited: 2D-3D Alignment via Surface Normal Prediction

Aayush Bansal, Bryan Russell, Abhinav Gupta

We introduce an approach that leverages surface normal predictions, along with appearance cues, to retrieve 3D models for objects depicted in 2D still images from a large CAD objec…

cs.CV2020

Contact and Human Dynamics from Monocular Video

Davis Rempe, Leonidas J. Guibas, Aaron Hertzmann +3

Existing deep models predict 2D and 3D kinematic poses from video that are approximately accurate, but contain visible errors that violate physical constraints, such as feet penetr…

cs.CV2019

Neural Re-Simulation for Generating Bounces in Single Images

Carlo Innamorati, Bryan Russell, Danny M. Kaufman +1

We introduce a method to generate videos of dynamic virtual objects plausibly interacting via collisions with a still image's environment. Given a starting trajectory, physically s…

cs.CV2017

Localizing Moments in Video with Natural Language

Lisa Anne Hendricks, Oliver Wang, Eli Shechtman +3

We consider retrieving a specific temporal segment, or moment, from a video given a natural language text description. Methods designed to retrieve whole video clips with natural l…

cs.CV2026

Autoregressive Modeling of Film with Applications in Video Montage

Marcelo Sandoval-Castañeda, Fabian Caba Heilbron, Shiry Ginosar +5

FilmGPT is an autoregressive transformer trained on a large movie corpus to learn the statistical patterns of film editing and select existing raw shots to create coherent video mo…

#video editing#autoregressive modeling#transformer#shot selection
cs.CV2025

Video-Guided Foley Sound Generation with Multimodal Controls

Ziyang Chen, Prem Seetharaman, Bryan Russell +4

Generating sound effects for videos often requires creating artistic sound effects that diverge significantly from real-life sources and flexible control in the sound design. To ad…

cs.CV2025

Discovering Divergent Representations between Text-to-Image Models

Lisa Dunlap, Joseph E. Gonzalez, Trevor Darrell +3

In this paper, we investigate when and how visual representations learned by two different generative models diverge. Given two text-to-image models, our goal is to discover visual…

cs.CV2018

BodyNet: Volumetric Inference of 3D Human Body Shapes

Gül Varol, Duygu Ceylan, Bryan Russell +4

Human shape estimation is an important task for video editing, animation and fashion industry. Predicting 3D human body shape from natural images, however, is highly challenging du…

cs.CV2015

Understanding deep features with computer-generated imagery

Mathieu Aubry, Bryan Russell

We introduce an approach for analyzing the variation of features generated by convolutional neural networks (CNNs) with respect to scene factors that occur in natural images. Such…

cs.CV2017

PixelNet: Representation of the pixels, by the pixels, and for the pixels

Aayush Bansal, Xinlei Chen, Bryan Russell +2

We explore design principles for general pixel-level prediction problems, from low-level edge detection to mid-level surface normal estimation to high-level semantic segmentation.…

cs.CV2020

Telling Left from Right: Learning Spatial Correspondence of Sight and Sound

Karren Yang, Bryan Russell, Justin Salamon

Self-supervised audio-visual learning aims to capture useful representations of video by leveraging correspondences between visual and audio inputs. Existing approaches have focuse…

cs.CV2023

Conditional Generation of Audio from Video via Foley Analogies

Yuexi Du, Ziyang Chen, Justin Salamon +2

The sound effects that designers add to videos are designed to convey a particular artistic effect and, thus, may be quite different from a scene's true sound. Inspired by the chal…