17 citations · 18 across the 6 of their papers we have counts for
8 papers
Foveated Reasoning: Stateful, Action-based Visual Focusing for Vision-Language Models
Juhong Min, Lazar Valkov, Vitali Petsiuk +2
Vision-language models benefit from high-resolution images, but the increase in visual-token count incurs high compute overhead. Humans resolve this tension via foveation: a coarse…
GoldiCLIP: The Goldilocks Approach for Balancing Explicit Supervision for Language-Image Pretraining
Deen Dayal Mohan, Hossein Souri, Vitali Petsiuk +4
Until recently, the success of large-scale vision-language models (VLMs) has primarily relied on billion-sample datasets, posing a significant barrier to progress. Latest works hav…
ARGENT: Adaptive Hierarchical Image-Text Representations
Chuong Huynh, Hossein Souri, Abhinav Kumar +3
Large-scale Vision-Language Models (VLMs) such as CLIP learn powerful semantic representations but operate in Euclidean space, which fails to capture the inherent hierarchical stru…
SCOT: Self-Supervised Contrastive Pretraining For Zero-Shot Compositional Retrieval
Bhavin Jawade, Joao V. B. Soares, Kapil Thadani +6
Compositional image retrieval (CIR) is a multimodal learning task where a model combines a query image with a user-provided text modification to retrieve a target image. CIR finds…
Deep Metric Learning for Computer Vision: A Brief Overview
Deen Dayal Mohan, Bhavin Jawade, Srirangaraj Setlur +1
Objective functions that optimize deep neural networks play a vital role in creating an enhanced feature representation of the input data. Although cross-entropy-based loss formula…
CoNAN: Conditional Neural Aggregation Network For Unconstrained Face Feature Fusion
Bhavin Jawade, Deen Dayal Mohan, Dennis Fedorishin +2
Face recognition from image sets acquired under unregulated and uncontrolled settings, such as at large distances, low resolutions, varying viewpoints, illumination, pose, and atmo…
RidgeBase: A Cross-Sensor Multi-Finger Contactless Fingerprint Dataset
Bhavin Jawade, Deen Dayal Mohan, Srirangaraj Setlur +2
Contactless fingerprint matching using smartphone cameras can alleviate major challenges of traditional fingerprint systems including hygienic acquisition, portability and presenta…
Hear The Flow: Optical Flow-Based Self-Supervised Visual Sound Source Localization
Dennis Fedorishin, Deen Dayal Mohan, Bhavin Jawade +2
Learning to localize the sound source in videos without explicit annotations is a novel area of audio-visual research. Existing work in this area focuses on creating attention maps…