Search Results for author:
Found 11 papers, 2 papers with code
GaussianVideo: Efficient Video Representation via Hierarchical Gaussian Splatting
To address these issues, we introduce a novel neural video representation that combines 3D Gaussian splatting with continuous camera motion modeling.
TransPixeler: Advancing Text-to-Video Generation with Transparency
Text-to-video generative models have made significant strides, enabling diverse applications in entertainment, advertising, and education.
Generative Video Propagation
Large-scale video generation models have the inherent ability to realistically model natural scenes.
Move-in-2D: 2D-Conditioned Human Motion Generation
Generating realistic human videos remains a challenging task, with the most effective methods currently relying on a human motion sequence as a control signal.
Generative Timelines for Instructed Visual Assembly
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 potentially even disabled users.
They're All Doctors: Synthesizing Diverse Counterfactuals to Mitigate Associative Bias
Vision Language Models (VLMs) such as CLIP are powerful models; however they can exhibit unwanted biases, making them less safe when deployed directly in applications such as text-to-image, text-to-video retrievals, reverse search, or classification tasks.
Koala: Key frame-conditioned long video-LLM
Long video question answering is a challenging task that involves recognizing short-term activities and reasoning about their fine-grained relationships.
GenLens: A Systematic Evaluation of Visual GenAI Model Outputs
This research underscores the importance of robust early-stage evaluation tools in GenAI development, contributing to the advancement of fair and high-quality GenAI models.
SoundCam: A Dataset for Finding Humans Using Room Acoustics
A room's acoustic properties are a product of the room's geometry, the objects within the room, and their specific positions.
RealImpact: A Dataset of Impact Sound Fields for Real Objects
Objects make unique sounds under different perturbations, environment conditions, and poses relative to the listener.
MonoTrack: Shuttle trajectory reconstruction from monocular badminton video
Trajectory estimation is a fundamental component of racket sport analytics, as the trajectory contains information not only about the winning and losing of each point, but also how it was won or lost.
Ranked #2 on
Sports Ball Detection and Tracking
on Basketball
