Angela Yao

25

Papers

267

Total Citations

Papers (25)

Can I Trust Your Answer? Visually Grounded Video Question Answering

Scaling for Training Time and Post-hoc Out-of-distribution Detection Enhancement

EgoTextVQA: Towards Egocentric Scene-Text Aware Video Question Answering

RealViformer: Investigating Attention for Real-World Video Super-Resolution

Make Me a BNN: A Simple Strategy for Estimating Bayesian Uncertainty from Pre-trained Models

Deep Imbalanced Regression via Hierarchical Classification Adjustment

SfM-Free 3D Gaussian Splatting via Hierarchical Training

KITRO: Refining Human Mesh by 2D Clues and Kinematic-tree Rotation

Context-Enhanced Memory-Refined Transformer for Online Action Detection

On the Consistency of Video Large Language Models in Temporal Comprehension

Streaming VideoLLMs for Real-Time Procedural Video Understanding

Visual Intention Grounding for Egocentric Assistants

Condensing Action Segmentation Datasets via Generative Network Inversion

On the Calibration of Human Pose Estimation

Analyzing the Synthetic-to-Real Domain Gap in 3D Hand Pose Estimation

The Devil is in the Spurious Correlations: Boosting Moment Retrieval with Dynamic Learning

Intermediate Connectors and Geometric Priors for Language-Guided Affordance Segmentation on Unseen Object Categories

Humans as Checkerboards: Calibrating Camera Motion Scale for World-Coordinate Human Mesh Recovery

A Constrained Optimization Approach for Gaussian Splatting from Coarsely-posed Images and Noisy Lidar Point Clouds

Geometric Alignment and Prior Modulation for View-Guided Point Cloud Completion on Unseen Categories

Diagnosing Pretrained Models for Out-of-distribution Detection

Coherent Temporal Synthesis for Incremental Action Segmentation

Enhancing Video Super-Resolution via Implicit Resampling-based Alignment

Semantics-aware Test-time Adaptation for 3D Human Pose Estimation

Deep Regression Representation Learning with Topology