papers

Publications (13)

cs.CV2026

WildProp: Visual Estimation of Wildlife Body Proportions at Scale

Mustafa Chasmai, Aaron Sun, Subhransu Maji

Population-level morphometric measurements underpin ecological and evolutionary studies but traditionally require controlled imaging or physical specimen handling, limiting scalabi…

cs.LG2026

MetaPerch: Learning from metadata for bioacoustics foundation models

Mustafa Chasmai, Vincent Dumoulin, Jenny Hamer

The paper presents MetaPerch, a bioacoustic foundation model that uses recording metadata (e.g., location, time) as auxiliary supervision to improve species identification performa…

#bioacoustics#foundation models#metadata supervision#species identification
cs.CV2026

RealBirdID: Benchmarking Bird Species Identification in the Era of MLLMs

Logan Lawrence, Mustafa Chasmai, Rangel Daroya +8

Fine-grained bird species identification in the wild is frequently unanswerable from a single image: key cues may be non-visual (e.g. vocalization), or obscured due to occlusion, c…

cs.CV2022

A View Independent Classification Framework for Yoga Postures

Mustafa Chasmai, Nirjhar Das, Aman Bhardwaj +1

Yoga is a globally acclaimed and widely recommended practice for a healthy living. Maintaining correct posture while performing a Yogasana is of utmost importance. In this work, we…

cs.CV2025

Moment Sampling in Video LLMs for Long-Form Video QA

Mustafa Chasmai, Gauri Jagatap, Gouthaman KV +3

Recent advancements in video large language models (Video LLMs) have significantly advanced the field of video question answering (VideoQA). While existing methods perform well on…

cs.SD2025

The iNaturalist Sounds Dataset

Mustafa Chasmai, Alexander Shepard, Subhransu Maji +1

We present the iNaturalist Sounds Dataset (iNatSounds), a collection of 230,000 audio files capturing sounds from over 5,500 species, contributed by more than 27,000 recordists wor…