Search

Previous methods usually only extract the image modality's information to recognize group activity. However, mining image information is approaching saturation, making it difficult to extract richer information. Therefore, extracting complementary information from other modalities to supplement image information has become increasingly important. In fact, action labels provide clear text information to express the action's semantics, which existing methods often overlook. Thus, we propose ActivityCLIP, a plug-and-play method for mining the text information contained in the action labels to supplement the image information for enhancing group activity recognition. ActivityCLIP consists of text and image branches, where the text branch is plugged into the image branch (The off-the-shelf image-based method). The text branch includes Image2Text and relation modeling modules. Specifically, we propose the knowledge transfer module, Image2Text, which adapts image information into text information extracted by CLIP via knowledge distillation. Further, to keep our method convenient, we add fewer trainable parameters based on the relation module of the image branch to model interaction relation in the text branch. To show our method's generality, we replicate three representative methods by ActivityCLIP, which adds only limited trainable parameters, achieving favorable performance improvements for each method. We also conduct extensive ablation studies and compare our method with state-of-the-art methods to demonstrate the effectiveness of ActivityCLIP.

The task of Group Activity Recognition (GAR) aims to predict the activity category of the group by learning the actor spatial-temporal interaction relation in the group. Therefore, an effective actor relation learning method is crucial for the GAR task. The previous works mainly learn the interaction relation by the well-designed GCNs or Transformers. For example, to infer the actor interaction relation, GCNs need a learnable adjacency, and Transformers need to calculate the self-attention. Although the above methods can model the interaction relation effectively, they also increase the complexity of the model (the number of parameters and computations). In this paper, we design a novel MLP-based method for Actor Interaction Relation learning (MLP-AIR) in GAR. Compared with GCNs and Transformers, our method has a competitive but conceptually and technically simple alternative, significantly reducing the complexity. Specifically, MLP-AIR includes three sub-modules: MLP-based Spatial relation modeling module (MLP-S), MLP-based Temporal relation modeling module (MLP-T), and MLP-based Relation refining module (MLP-R). MLP-S is used to model the spatial relation between different actors in each frame. MLP-T is used to model the temporal relation between different frames for each actor. MLP-R is used further to refine the relation between different dimensions of relation features to improve the feature's expression ability. To evaluate the MLP-AIR, we conduct extensive experiments on two widely used benchmarks, including the Volleyball and Collective Activity datasets. Experimental results demonstrate that MLP-AIR can get competitive results but with low complexity., Comment: Submit to Neurocomputing

We provide two sufficient and necessary conditions to characterize any $n$-bit partial Boolean function with exact quantum 1-query complexity. Using the first characterization, we present all $n$-bit partial Boolean functions that depend on $n$ bits and have exact quantum 1-query complexity. Due to the second characterization, we construct a function $F$ that maps any $n$-bit partial Boolean function to some integer, and if an $n$-bit partial Boolean function $f$ depends on $k$ bits and has exact quantum 1-query complexity, then $F(f)$ is non-positive. In addition, we show that the number of all $n$-bit partial Boolean functions that depend on $k$ bits and have exact quantum 1-query complexity is not bigger than $n^{2}2^{2^{n-1}(1+2^{2-k})+2n^{2}}$ for all $n\geq 3$ and $k\geq 2$., Comment: 11pages; comments are welcome

We study the electronic transport properties of two-dimensional (2D) fully-hydrogenated borophene (namely, borophane), using the density functional theory and non-equilibrium Green's function approaches. Borophane shows a perfect electrical transport anisotropy and is promising for applications. Along the peak- or equivalently the valley-parallel direction, the 2D borophane exhibits a metallic characteristic and its current-voltage (I-V) curve shows a linear behavior, corresponding to the ON state in borophane-based nano-switch. In this case, electrons mainly propagate via the B-B bonds along the linear boron chains. In contrast, the electron transmission is almost forbidden along the perpendicular buckled direction (i.e., the OFF state), due to its semi-conductor property. Our work demonstrates that 2D borophane could combine the metal and semiconductor features and can be a promising candidate of nano-switching materials with stable structure and high ON/OFF ratio.

In this paper, several discrete schemes for Gaussian curvature are surveyed. The convergence property of a modified discrete scheme for the Gaussian curvature is considered. Furthermore, a new discrete scheme for Gaussian curvature is resented. We prove that the new scheme converges at the regular vertex with valence not less than 5. By constructing a counterexample, we also show that it is impossible for building a discrete scheme for Gaussian curvature which converges over the regular vertex with valence 4. Finally, asymptotic errors of several discrete scheme for Gaussian curvature are compared.