SKA-VCT: Listening to the Motion
Physical consistency for audio-visual segmentation
A research project on locating sounding objects by aligning audio spectra with motion evidence instead of trusting static visual saliency alone.
- Uses spectral-kinematic alignment to retrieve sound-activated motion cues.
- Adds motion-prompted query generation to focus segmentation on genuine sounding objects.
- Targets false positives caused by salient but silent objects.

