Lee, Seunghoon Cho, Suhwan Lee, Dogyoon Lee, Minhyeok Lee, Sangyoun 2024-03-07T06:30:16Z 2024-03-07T06:30:16Z 2024-03-07 2023-10 https://pubs.kist.re.kr/handle/201004/149420 Unsupervised Video Object Segmentation (UVOS) refers to the challenging task of segmenting the prominent object in videos without manual guidance. In recent works, two approaches for UVOS have been discussed that can be divided into: appearance and appearance-motion-based methods, which have limitations respectively. Appearance-based methods do not consider the motion of the target object due to exploiting the correlation information between randomly paired frames. Appearance-motion-based methods have the limitation that the dependency on optical flow is dominant due to fusing the appearance with motion. In this paper, we propose a novel framework for UVOS that can address the aforementioned limitations of the two approaches in terms of both time and scale. Temporal Alignment Fusion aligns the saliency information of adjacent frames with the target frame to leverage the information of adjacent frames. Scale Alignment Decoder predicts the target object mask by aggregating multi-scale feature maps via continuous mapping with implicit neural representation. We present experimental results on public benchmark datasets, DAVIS 2016 and FBMS, which demonstrate the effectiveness of our method. Furthermore, we outperform the state-of-the-art methods on DAVIS 2016. English IEEE TSANET: TEMPORAL AND SCALE ALIGNMENT FOR UNSUPERVISED VIDEO OBJECT SEGMENTATION Conference 10.1109/ICIP49359.2023.10222236 1 30th IEEE International Conference on Image Processing (ICIP), pp.1535 - 1539 30th IEEE International Conference on Image Processing (ICIP) 1535 1539 US Kuala Lumpur, MALAYSIA 2023-10-08 2023 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING, ICIP 001106821001123 2-s2.0-85180811374