Existing action counting methods typically rely on pixel-based changes within videos, leading to high computational redundancy and low accuracy due to the limited spatial sensitivity. To address these challenges, we introduce MoCount, the first framework that leverages 3D motion representations for counting tasks. MoCount significantly reduces computational overhead and improves counting accuracy, benefiting from the simplicity of motion representation and strong spatial sensitivity. Specifically, we utilize a motion estimator to convert video subjects into 3D motion data. A motion encoder, combined with a Sparse Spatial-Temporal module, is then applied to extract robust human body representations, yielding precise counting results. Extensive experiments on the RepCount and UCFRep datasets show that MoCount achieves state-of-the-art performance, reducing inference latency by approximately 2-3 times compared to existing video counting models. These advantages position MoCount as a leading solution for real-world action counting applications.

With the explosive growth of short texts on users' preferences, learning discriminative and coherent latent topics from short texts is a critical work, since many practical applications require semantic understandings that short texts convey explicitly and implicitly. However, existing short text topic learning methods face the challenge of fully capturing semantically related co-occurrence phrases. Therefore, this paper proposes a novel Heterogeneous Information Network-based Short Text Topic learning approach (HIN-ShoTT) in terms of parts of speech, without depending on any auxiliary information. Specifically, HIN-ShoTT can be decomposed into three phases: i) seeking semantic relations among words, where HIN-ShoTT models multiple semantic relations among words based on a Heterogeneous Information Network (HIN) in terms of parts of speech; ii) extracting co-occurrence phrases and filtering noises, where HIN-ShoTT defines parts-of-speech meta structures to guide co-occurrence phrase extraction and a self-adapting threshold filtering module is proposed for discarding noises; and iii) inferring topics, where HIN-ShoTT models the generative process of co-occurrence phrases to make topic learning effective with the abundant corpus-level information. Our experimental results on three real-world datasets not only show that HIN-ShoTT performs well, but also demonstrate that it is feasible to incorporate HIN into short text topic learning for accuracy improvement.

The authors propose a terse texture feature, called the dominant centre‐symmetric local binary pattern (DCSLBP), which has similar distinctiveness and half dimension compared against original centre‐symmetric local binary pattern (CS‐LBP). On the basis of DCSLBP histogram and an improved construction, a compact descriptor for local feature is presented. To assess the proposed descriptor with the state‐of‐the‐art in performance and dimension, the authors extend it to two variants with different dimensions using the existing method. These descriptors are compared with scale‐invariant feature transform (SIFT), multisupport region rotation and intensity monotonic invariant descriptor (MRRID), orthagonal combination local binary pattern (OC‐LBP) in interest region matching and in the application of object recognition. The experiments demonstrate the proposed descriptor's compactness and robustness to various image transformations, especially to large illumination change.