Active learning is a label-efficient machine learning method that actively selects the most
valuable unlabeled samples to annotate. Active learning focuses on achieving the best …

Precise fish metric estimation is essential in providing intelligent aquaculture farm decisions.
Stereo vision has been widely used for size estimation. Still, many factors affect fish metrics …

The dimensions of cost volumes and corresponding aggregation networks play a critical role
in balancing the speed and accuracy for stereo matching. Current most 2D stereo networks …

We introduce Double Cost Volume Stereo Matching Network (DCVSMNet) which is a novel
architecture characterised by by two small upper (group-wise) and lower (norm correlation) …

Despite recent stereo matching algorithms achieving significant results on public
benchmarks, the problem of requiring heavy computation remains unsolved. Most works …

Depth estimation from stereo images is an important task in computer vision. Despite of the
great contributions that are made in this field, most matching‐based methods still face the …