papers

Publications (14)

cs.CV2021

PiCIE: Unsupervised Semantic Segmentation using Invariance and Equivariance in Clustering

Jang Hyun Cho, Utkarsh Mall, Kavita Bala +1

We present a new framework for semantic segmentation without annotations via clustering. Off-the-shelf clustering methods are limited to curated, single-label, and object-centric i…

cs.CV2021

Field-Guide-Inspired Zero-Shot Learning

Utkarsh Mall, Bharath Hariharan, Kavita Bala

Modern recognition systems require large amounts of supervision to achieve accuracy. Adapting to new domains requires significant data from experts, which is onerous and can become…

cs.CV2026

Flat-Pack Bench: Evaluating Spatio-Temporal Understanding in Large Vision-Language Models through Furniture Assembly

Aditya Chetan, Eric Cai, Peeyush Kushwaha +5

The emergence of Large Vision-Language Models (LVLMs) has significantly advanced video understanding capabilities. However, existing benchmarks focus predominantly on coarse-graine…

cs.CV2020

Discovering Underground Maps from Fashion

Utkarsh Mall, Kavita Bala, Tamara Berg +1

The fashion sense -- meaning the clothing styles people wear -- in a geographical region can reveal information about that region. For example, it can reflect the kind of activitie…

cs.AI2025

Towards LLM Agents for Earth Observation

Chia Hsiang Kao, Wenting Zhao, Shreelekha Revankar +8

Earth Observation (EO) provides critical planetary data for environmental monitoring, disaster management, climate science, and other scientific domains. Here we ask: Are AI system…

cs.CV2024

How Video Meetings Change Your Expression

Sumit Sarin, Utkarsh Mall, Purva Tendulkar +1

Do our facial expressions change when we speak over video calls? Given two unpaired sets of videos of people, we seek to automatically find spatio-temporal patterns that are distin…

cs.CV2024

AllClear: A Comprehensive Dataset and Benchmark for Cloud Removal in Satellite Imagery

Hangyu Zhou, Chia-Hsiang Kao, Cheng Perng Phoo +3

Clouds in satellite imagery pose a significant challenge for downstream applications. A major challenge in current cloud removal research is the absence of a comprehensive benchmar…

cs.CV2023

Remote Sensing Vision-Language Foundation Models without Annotations via Ground Remote Alignment

Utkarsh Mall, Cheng Perng Phoo, Meilin Kelsey Liu +3

We introduce a method to train vision-language models for remote-sensing images without using any textual annotations. Our key insight is to use co-located internet imagery taken o…

cs.CV2025

MONITRS: Multimodal Observations of Natural Incidents Through Remote Sensing

Shreelekha Revankar, Utkarsh Mall, Cheng Perng Phoo +2

Natural disasters cause devastating damage to communities and infrastructure every year. Effective disaster response is hampered by the difficulty of accessing affected areas durin…

cs.CV2019

GeoStyle: Discovering Fashion Trends and Events

Utkarsh Mall, Kevin Matzen, Bharath Hariharan +2

Understanding fashion styles and trends is of great potential interest to retailers and consumers alike. The photos people upload to social media are a historical and public data s…

cs.CV2025

Scale-Aware Recognition in Satellite Images under Resource Constraints

Shreelekha Revankar, Cheng Perng Phoo, Utkarsh Mall +2

Recognition of features in satellite imagery (forests, swimming pools, etc.) depends strongly on the spatial scale of the concept and therefore the resolution of the images. This p…

cs.CV2024

Evolving Interpretable Visual Classifiers with Large Language Models

Mia Chiquier, Utkarsh Mall, Carl Vondrick

Multimodal pre-trained models, such as CLIP, are popular for zero-shot classification due to their open-vocabulary flexibility and high performance. However, vision-language models…

cs.GR2017

A Deep Recurrent Framework for Cleaning Motion Capture Data

Utkarsh Mall, G. Roshan Lal, Siddhartha Chaudhuri +1

We present a deep, bidirectional, recurrent framework for cleaning noisy and incomplete motion capture data. It exploits temporal coherence and joint correlations to infer adaptive…

cs.CV2025

DiSciPLE: Learning Interpretable Programs for Scientific Visual Discovery

Utkarsh Mall, Cheng Perng Phoo, Mia Chiquier +3

Visual data is used in numerous different scientific workflows ranging from remote sensing to ecology. As the amount of observation data increases, the challenge is not just to mak…