ResearchAlpha Leak

Conferences Topics Top Authors Rankings Browse All

Home/Authors/Bhiksha Raj

Bhiksha Raj

Topic trends: 32,543 papers · similarity ≥ 0.4 · year ≥ 2024 · Data sourced from Semantic Scholar

34,598 papers | Abstracts: 31,650 (91.5%) | Citations: 34,598 (100.0%) | arXiv: 26,074 (75.4%)

Built: Feb 15, 2026, 12:57 AM AMS

23

papers

492

total citations

papers (23)

USB: A Unified Semi-supervised Learning Benchmark for Classification

NEURIPS 2022arXiv

ImageFolder: Autoregressive Image Generation with Folded Tokens

The Right To Talk: An Audio-Visual Transformer Approach

FREDOM: Fairness Domain Adaptation Approach to Semantic Scene Understanding

SoftVQ-VAE: Efficient 1-Dimensional Continuous Tokenizer

Audio Entailment: Assessing Deductive Reasoning for Audio Understanding

Self-Supervised 3D Face Reconstruction via Conditional Estimation

Weakly-Supervised Audio-Visual Segmentation

NEURIPS 2023arXiv

Fairness Continual Learning Approach to Semantic Scene Understanding in Open-World Environments

NEURIPS 2023arXiv

Mellow: a small audio language model for reasoning

NEURIPS 2025arXiv

QDFormer: Towards Robust Audiovisual Segmentation in Complex Environments with Quantization-based Semantic Decomposition

Synergistic Global-space Camera and Human Reconstruction from Videos

ADIFF: Explaining audio difference using natural language

Pairwise Similarity Learning is SimPLE

A General Framework for Learning from Weak Supervision

FALCON: Fairness Learning via Contrastive Attention Approach to Continual Semantic Scene Understanding

Training on Foveated Images Improves Robustness to Adversarial Attacks

NEURIPS 2023arXiv

Completing Visual Objects via Bridging Generation and Segmentation

Toward Material-Agnostic System Identification from Videos

Is normalization indispensable for training deep neural network?

Robust Referring Video Object Segmentation with Cyclic Structural Consensus

Contrast and Order Representations for Video Self-Supervised Learning

PaintSeg: Painting Pixels for Training-free Segmentation