Space computing devices expand handwritten input from two-dimensional screens into three-dimensional space, providing an unrestricted interactive experience. Due to the high degree of freedom and lack of tactile feedback in in-air handwriting, handwritten characters not only become less legible but also lose the writer's personal style. This paper proposes a method for reconstructing discrete in-air handwriting using continuous diffusion models, capturing the writing process and style from a small number of user-provided handwritten tracks and images, to restore the legibility of characters and mimics the writer's style. We represent handwritten track data in binary form and model it with continuous diffusion models, recovering discrete handwritten track data through threshold processing. Our approach reconstructs in-air handwritten characters in two stages. During the content preservation phase, we propose a partial noise injection strategy based on reference sequence modeling, using the content information of the original character as a guiding condition to maintain content consistency in handwritten character. In the style aggregation phase, we adaptively fuse the visual style of the handwritten in the image modality with the dynamic writing process in the sequence modality, overcoming issues of insufficient style capture due to noise interference in the backward process. Qualitative and quantitative experiments demonstrate the superiority of our method.

Tag-based social image search predominately focus on using user-annotated tags to find out the results of user query. However, the performance of tag-based social image search is usually unable to satisfy the needs of users. In this paper, we propose a novel framework based on Social Relationship Graph for Social Image Search (SRGSIS), which involves two stages. In the first stage, we use heterogeneous data from multiple modalities to build a social relationship graph. Then, for the given query keywords, we execute an efficient keyword search algorithm over the social relationship graph and obtain top-k candidate results based on relevance score. We model these results as the answer trees connecting keyword nodes that match keywords in the query. In the second stage, for refining the candidate results, each image in social relationship graph is represented as a region adjacency graph by using the visual content of image. We further model these region adjacency graphs as a closure tree and compute approximate graph similarity between the candidate results and the closure tree to obtain more desirable results. Extensive experimental results demonstrate the effectiveness of the proposed approach.

Concept-Based Semantic Video Retrieval(CBSVR) usually uses semantic representations of videos to handle user's retrieval requests. It is obvious that the accuracy of semantic video retrieval depends on results of concept detectors, but the detection results are usually imprecise and uncertain . In this paper, we propose a multi-information fusion approach (MIF) which is dedicated to solving the problem of uncertain semantic representations of videos for improving retrieval accuracy. This approach is based on a novel two-phase framework that involves the inferring phase and the fusing phase. In the inferring phase, the most relevant concepts to the user's query are chosen by exploring both contextual correlation among concepts and temporal correlation among shots. In the fusing phase, the inferred probabilities of the related concepts are fused together with the detection results via minimization of potential function to refine the detector prediction. Experiments on the widely used TRECVID datasets demonstrate that our approach can effectively improve the accuracy of semantic concept detection.