Problem
Research questions and friction points this paper is trying to address.
salient object detection
user needs
visual stimuli
UserSOD
proactive needs
Determined by User Needs: A Salient Object Detection Rationale Beyond Conventional Visual Stimuli
🤖 AI Summary
Traditional salient object detection relies solely on visual stimuli, neglecting users’ active intentions and thus struggling to adapt to real-world tasks. This work proposes a novel user-driven paradigm for salient object detection (UserSOD), which, for the first time, incorporates user intent into saliency modeling, prioritizing task-specific demands over bottom-up visual input to guide attention. To realize this paradigm, we introduce the first dedicated UserSOD framework and address the critical bottleneck of lacking annotated data in this emerging direction. Experimental results demonstrate that our approach establishes a more accurate foundation for downstream applications such as fine-grained gaze sequence prediction and scene understanding, significantly enhancing both performance and user experience.
📝 Abstract
Existing \textbf{s}alient \textbf{o}bject \textbf{d}etection (SOD) methods adopt a \textbf{passive} visual stimulus-based rationale--objects with the strongest visual stimuli are perceived as the user's primary focus (i.e., salient objects). They ignore the decisive role of users' \textbf{proactive needs} in segmenting salient objects--if a user has a need before seeing an image, the user's salient objects align with their needs, e.g., if a user's need is ``white apple'', when this user sees an image, the user's primary focus is on the ``white apple'' or ``the most white apple-like'' objects in the image. Such an oversight not only \textbf{fails to satisfy users}, but also \textbf{limits the development of downstream tasks}. For instance, in salient object ranking tasks, focusing solely on visual stimuli-based salient objects is insufficient for conducting an analysis of fine-grained relationships between users' viewing order (usually determined by user's needs) and scenes, which may result in wrong ranking results. Clearly, it is essential to detect salient objects based on user needs. Thus, we advocate a \textbf{User} \textbf{S}alient \textbf{O}bject \textbf{D}etection (UserSOD) task, which focuses on \textbf{detecting salient objects align with users' proactive needs when user have needs}. The main challenge for this new task is the lack of datasets for model training and testing.
Innovation
Methods, ideas, or system contributions that make the work stand out.
User Salient Object Detection
User Needs
Visual Stimuli
Proactive Attention
Salient Object Ranking
🔎 Similar Papers
No similar papers found.
