Venu Govindaraju — accepted AI-conference papers

2026

Forget Less by Learning from Parents Through Hierarchical Relationships

Arjun Ramesh Kaushik, Naresh Kumar Devulapally, Vishnu Suresh Lokhande, Nalini K. Ratha, Venu Govindaraju

AAAI 2026technical

Custom Diffusion Models (CDMs) offer impressive capabilities for personalization in generative modeling, yet they remain vulnerable to catastrophic forgetting when learning new concepts sequentially. Existing approaches primarily focus on minimizing interference between concepts, often neglecting th

Cited by 0 Source ↗PDF ↗Scholar ↗

2026

LABEL-FREE MITIGATION OF SPURIOUS CORRELATIONS IN VLMS USING SPARSE AUTOENCODERS

Bharat Chandra Yalavarthi, Nalini K. Ratha, Venu Govindaraju

ICLR 2026poster

Vision-Language Models (VLMs) have demonstrated impressive zero-shot capabilities across a wide range of tasks and domains. However, their performance is often compromised by learned spurious correlations, which can adversely affect downstream applications. Existing mitigation strategies typically d…

Cited by 0 Source ↗code ↗Scholar ↗

2024

Audio Match Cutting: Finding and Creating Matching Audio Transitions in Movies and Videos

Dennis Fedorishin, Lie Lu, Srirangaraj Setlur, Venu Govindaraju

ICASSP 2024accepted

A "match cut" is a common video editing technique where a pair of shots that have a similar composition transition fluidly from one to another. Although match cuts are often visual, certain match cuts involve the fluid transition of audio, where sounds from different sources merge into one indisting…

Cited by 0 Source ↗Scholar ↗

2024

Fine-Grained Engine Fault Sound Event Detection Using Multimodal Signals

Dennis Fedorishin, Livio Forte, Philip Schneider, Srirangaraj Setlur, Venu Govindaraju

ICASSP 2024accepted

Sound event detection (SED) is an active area of audio research that aims to detect the temporal occurrence of sounds. In this paper, we apply SED to engine fault detection by introducing a multimodal SED framework that detects fine-grained engine faults of automobile engines using audio and acceler…

Cited by 0 Source ↗Scholar ↗

2024

ProxyFusion: Face Feature Aggregation Through Sparse Experts

Bhavin Jawade, Alexander Stone, Deen Dayal Mohan, Xiao Wang, Srirangaraj Setlur, Venu Govindaraju

NeurIPS 2024poster

Face feature fusion is indispensable for robust face recognition, particularly in scenarios involving long-range, low-resolution media (unconstrained environments) where not all frames or features are equally informative. Existing methods often rely on large intermediate feature maps or face metadat…

Cited by 0 Source ↗PDF ↗code ↗Scholar ↗

2020

Moving in the Right Direction: A Regularization for Deep Metric Learning

Deen Dayal Mohan, Nishant Sankaran, Dennis Fedorishin, Srirangaraj Setlur, Venu Govindaraju

CVPR 2020poster

Deep metric learning leverages carefully designed sampling strategies and loss functions that aid in optimizing the generation of a discriminable embedding space. While effective sampling of pairs is critical for shaping the metric space during training, the relative interactions between pairs, and…

Cited by 45 PDF ↗Scholar ↗

2016

Normalization Propagation: A Parametric Technique for Removing Internal Covariate Shift in Deep Networks

Devansh Arpit, Yingbo Zhou, Bhargava Kota, Venu Govindaraju

ICML 2016poster

While the authors of Batch Normalization (BN) identify and address an important problem involved in training deep networks– \textitInternal Covariate Shift– the current solution has certain drawbacks. For instance, BN depends on batch statistics for layerwise input normalization during training whic…

Cited by 154 Source ↗PDF ↗Scholar ↗

2016

Why Regularized Auto-Encoders learn Sparse Representation?

Devansh Arpit, Yingbo Zhou, Hung Ngo, Venu Govindaraju

ICML 2016poster

Sparse distributed representation is the key to learning useful features in deep learning algorithms, because not only it is an efficient mode of data representation, but also – more importantly – it captures the generation process of most real world data. While a number of regularized auto-encoders…

Cited by 97 Source ↗PDF ↗Scholar ↗