7 papers
MetaPerch: Learning from metadata for bioacoustics foundation models
Mustafa Chasmai, Vincent Dumoulin, Jenny Hamer
Bioacoustic foundation models rely on large-scale citizen science platforms like Xeno-Canto for geographically and ecologically diverse data. Recent work has shown that supervision…
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…
Masked Autoencoders with Limited Data: Does It Work? A Fine-Grained Bioacoustics Case Study
Wuao Liu, Mustafa Chasmai, Subhransu Maji +1
Bioacoustic recognition requires fine-grained acoustic understanding to distinguish similar-sounding species. However, many large-scale data repositories such as iNaturalist are we…
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…
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…
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…
Bioacoustic Geolocation: Species Sounds as Geographic Signals
Mustafa Chasmai, Wuao Liu, Subhransu Maji +1
Can we determine someone's geographic location solely from the sounds they hear? Are acoustic signals enough to localize within a country, state, or even city? In this work, we tac…