Picture for Uttaran Bhattacharya

Uttaran Bhattacharya

HUMOTO: A 4D Dataset of Mocap Human Object Interactions

Add code
Apr 14, 2025
Viaarxiv icon

Evaluation and Incident Prevention in an Enterprise AI Assistant

Add code
Apr 11, 2025
Viaarxiv icon

Shape My Moves: Text-Driven Shape-Aware Synthesis of Human Motions

Add code
Apr 04, 2025
Viaarxiv icon

Speech2UnifiedExpressions: Synchronous Synthesis of Co-Speech Affective Face and Body Expressions from Affordable Inputs

Add code
Jun 26, 2024
Figure 1 for Speech2UnifiedExpressions: Synchronous Synthesis of Co-Speech Affective Face and Body Expressions from Affordable Inputs
Figure 2 for Speech2UnifiedExpressions: Synchronous Synthesis of Co-Speech Affective Face and Body Expressions from Affordable Inputs
Figure 3 for Speech2UnifiedExpressions: Synchronous Synthesis of Co-Speech Affective Face and Body Expressions from Affordable Inputs
Figure 4 for Speech2UnifiedExpressions: Synchronous Synthesis of Co-Speech Affective Face and Body Expressions from Affordable Inputs
Viaarxiv icon

HanDiffuser: Text-to-Image Generation With Realistic Hand Appearances

Add code
Mar 04, 2024
Figure 1 for HanDiffuser: Text-to-Image Generation With Realistic Hand Appearances
Figure 2 for HanDiffuser: Text-to-Image Generation With Realistic Hand Appearances
Figure 3 for HanDiffuser: Text-to-Image Generation With Realistic Hand Appearances
Figure 4 for HanDiffuser: Text-to-Image Generation With Realistic Hand Appearances
Viaarxiv icon

VaQuitA: Enhancing Alignment in LLM-Assisted Video Understanding

Add code
Dec 04, 2023
Figure 1 for VaQuitA: Enhancing Alignment in LLM-Assisted Video Understanding
Figure 2 for VaQuitA: Enhancing Alignment in LLM-Assisted Video Understanding
Figure 3 for VaQuitA: Enhancing Alignment in LLM-Assisted Video Understanding
Figure 4 for VaQuitA: Enhancing Alignment in LLM-Assisted Video Understanding
Viaarxiv icon

Large Content And Behavior Models To Understand, Simulate, And Optimize Content And Behavior

Add code
Sep 08, 2023
Figure 1 for Large Content And Behavior Models To Understand, Simulate, And Optimize Content And Behavior
Figure 2 for Large Content And Behavior Models To Understand, Simulate, And Optimize Content And Behavior
Figure 3 for Large Content And Behavior Models To Understand, Simulate, And Optimize Content And Behavior
Figure 4 for Large Content And Behavior Models To Understand, Simulate, And Optimize Content And Behavior
Viaarxiv icon

Show Me What I Like: Detecting User-Specific Video Highlights Using Content-Based Multi-Head Attention

Add code
Jul 19, 2022
Viaarxiv icon

HighlightMe: Detecting Highlights from Human-Centric Videos

Add code
Oct 05, 2021
Figure 1 for HighlightMe: Detecting Highlights from Human-Centric Videos
Figure 2 for HighlightMe: Detecting Highlights from Human-Centric Videos
Figure 3 for HighlightMe: Detecting Highlights from Human-Centric Videos
Figure 4 for HighlightMe: Detecting Highlights from Human-Centric Videos
Viaarxiv icon

Speech2AffectiveGestures: Synthesizing Co-Speech Gestures with Generative Adversarial Affective Expression Learning

Add code
Aug 03, 2021
Figure 1 for Speech2AffectiveGestures: Synthesizing Co-Speech Gestures with Generative Adversarial Affective Expression Learning
Figure 2 for Speech2AffectiveGestures: Synthesizing Co-Speech Gestures with Generative Adversarial Affective Expression Learning
Figure 3 for Speech2AffectiveGestures: Synthesizing Co-Speech Gestures with Generative Adversarial Affective Expression Learning
Figure 4 for Speech2AffectiveGestures: Synthesizing Co-Speech Gestures with Generative Adversarial Affective Expression Learning
Viaarxiv icon