Search for: All records

While image captioning provides isolated descriptions for individual images, and video captioning offers one single narrative for an entire video clip, our work explores an important middle ground: progress-aware video captioning at the frame level. This novel task aims to generate temporally fine-grained captions that not only accurately describe each frame but also capture the subtle progression of actions throughout a video sequence. Despite the strong capabilities of existing leading vision language models, they often struggle to discern the nuances of frame-wise differences. To address this, we propose ProgressCaptioner, a captioning model designed to capture the fine-grained temporal dynamics within an action sequence. Alongside, we develop the FrameCap dataset to support training and the FrameCapEval benchmark to assess caption quality. The results demonstrate that ProgressCaptioner significantly surpasses leading captioning models, producing precise captions that accurately capture action progression and set a new standard for temporal precision in video captioning. Finally, we showcase practical applications of our approach, specifically in aiding keyframe selection and advancing video understanding, highlighting its broad utility. 

The vestibular system (VS) allows humans to have a sense of balance and orientation. Within the VS, fluid displacement occurs within the ear canal, triggering nerve signals to be translated by the nervous system, allowing for the interpretation of the head's orientation. When there is a disturbance to this system, vestibular dysfunction occurs potentially causing vertigo and a loss of balance. It is estimated that 35 percent of adults 40 years or older in the United States have experienced vestibular dysfunction. The vestibular balance system poses a robust, unique topic for developing interdisciplinary education curricula as its function encapsulates many fundamental mechanical, chemical, biological, and physical phenomena that can be studied with engineering concepts and principles. In this work, we present a survey of models of the vestibular sensory system. Following which, selected models are presented in an experiential learning format for students to better understand the relationship and sensitivity of model parameters and external stimuli to physiological system behavior. By conducting simulations of these models, students can visualize outcomes, pose questions, and potentially identify areas of research interest. This paper is the outcome of an Innovations in Graduate Education project supported by the National Science Foundation. The authors are graduate students from three engineering majors from the University of Massachusetts Lowell and the University of the District of Columbia co-creating an educational module with faculty and experts on human balance. The developed module related to analyzing the vestibular balance system mechanics will be integrated into undergraduate courses across engineering departments in partnering institutions. 

The vestibular system (VS) allows humans to have a sense of balance and orientation. Within the VS, fluid displacement occurs within the ear canal, triggering nerve signals to be translated by the nervous system, allowing for the interpretation of the head's orientation. When there is a disturbance to this system, vestibular dysfunction occurs potentially causing vertigo and a loss of. balance. It is estimated that 35 percent of adults 40 years or older in the United States have experienced vestibular dysfunction. The vestibular balance system poses a robust, unique topic for developing interdisciplinary education curricula as its function encapsulates many fundamental mechanical, chemical, biological, and physical phenomena that can be studied with engineering concepts and principles. In this work, we present a survey of models of the vestibular sensory system. Following which, selected models are presented in an experiential learning format for students to better understand the relationship and sensitivity of model parameters and external stimuli to physiological system behavior. By conducting simulations of these models, students can visualize outcomes, pose questions, and potentially identify areas of research interest. This paper is the outcome of an Innovations in Graduate Education project supported by the National Science Foundation. The authors are graduate students from three engineering majors from the University of Massachusetts Lowell and the University of the District of Columbia co-creating an educational module with faculty and experts on human balance. The developed module related to analyzing the vestibular balance system mechanics will be integrated into undergraduate courses across engineering departments in partnering institutions. 

Two new bopyrids, Bopyrinina articulata n. sp. and Bopyrinella asymmetrica n. sp. are described from French Polynesia, the Red Sea, and the Philippines. Bopyrinina articulata n.sp. infests Salmoneus cf. gracilipes Miya, and is distinguishable from other species of this genus by the structure of the maxilliped, pleopods and oostegite 1. Bopyrinella asymmetrica n. sp. is most similar to Bopyrinella albida Shiino, 1958, but females differ from that species because all pereomeres on the short side have round dorsolateral bosses and its pleotelson is greatly distorted. Bopyrina ocellata (Czerniavsky, 1868) is newly recorded from the Western Atlantic, from Florida, USA. Review of the species of Bopyrina revealed that B. choprai Nierstrasz & Brender à Brandis, 1929 and B. sewelli Chopra, 1930 are intermediate in morphology between Bopyrina and Schizobopyrina, the taxonomic assignment of these two species needs further evaluation. Keys to Bopyrinella Nierstrasz & Brender à Brandis, 1925 and Bopyrina Kossmann, 1881 are presented. Hosts and distributions of the seven species of Bopyrinella are summarized. 

The key challenge in photorealistic style transfer is that an algorithm should faithfully transfer the style of a reference photo to a content photo while the generated image should look like one captured by a camera. Although several photorealistic style transfer algorithms have been proposed, they need to rely on post- and/or pre-processing to make the generated images look photorealistic. If we disable the additional processing, these algorithms would fail to produce plausible photorealistic stylization in terms of detail preservation and photorealism. In this work, we propose an effective solution to these issues. Our method consists of a construction step (C-step) to build a photorealistic stylization network and a pruning step (P-step) for acceleration. In the C-step, we propose a dense auto-encoder named PhotoNet based on a carefully designed pre-analysis. PhotoNet integrates a feature aggregation module (BFA) and instance normalized skip links (INSL). To generate faithful stylization, we introduce multiple style transfer modules in the decoder and INSLs. PhotoNet significantly outperforms existing algorithms in terms of both efficiency and effectiveness. In the P-step, we adopt a neural architecture search method to accelerate PhotoNet. We propose an automatic network pruning framework in the manner of teacher-student learning for photorealistic stylization. The network architecture named PhotoNAS resulted from the search achieves significant acceleration over PhotoNet while keeping the stylization effects almost intact. We conduct extensive experiments on both image and video transfer. The results show that our method can produce favorable results while achieving 20-30 times acceleration in comparison with the existing state-of-the-art approaches. It is worth noting that the proposed algorithm accomplishes better performance without any pre- or post-processing.