Recently, cross-spectral image patch matching methods based on feature difference aggregation have achieved excellent performance, but they introduce a large number of parameters, limit matching speed and have poor scalability. At the same time, only using feature difference learning to extract differential features will lead to the loss of consistent features between cross-spectral image patches. Therefore, we construct a novel four-branch efficient feature relation learning network (EFR-Net) without feature difference aggregation. Specifically, a new four-branch feature relation learning strategy is proposed, which reasonably combines multiple feature relation learning to comprehensively and effectively extract the differential features and consistent features between image patches. At the same time, we construct an efficient local attention (ELA) module with negligible parameters, which can learn some global context information, enhance the interaction of local information and promote the extraction of discriminative features. In addition, a combined metric network is introduced to facilitate network optimization and improve network generalization. Furthermore, a public optical and SAR image patch matching dataset with a patch size of 64 × 64 pixels is constructed based on the OS dataset, which is called the OS patch dataset. We also establish an experimental benchmark on this new dataset. Extensive experimental results show that the proposed EFR-Net achieves excellent performance on cross-spectral image patch matching (OS patch dataset, VIS-NIR patch dataset) and single spectral image patch matching (Brown dataset).

Recently, feature relation learning has attracted extensive attention in cross-spectral image patch matching. However, most feature relation learning methods can only extract shallow feature relations and are accompanied by the loss of useful discriminative features or the introduction of disturbing features. Although the latest multi-branch feature difference learning network can relatively sufficiently extract useful discriminative features, the multi-branch network structure it adopts has a large number of parameters. Therefore, we propose a novel two-branch feature interaction learning network (FIL-Net). Specifically, a novel feature interaction learning idea for cross-spectral image patch matching is proposed, and a new feature interaction learning module is constructed, which can effectively mine common and private features between cross-spectral image patches, and extract richer and deeper feature relations with invariance and discriminability. At the same time, we re-explore the feature extraction network for the cross-spectral image patch matching task, and a new two-branch residual feature extraction network with stronger feature extraction capabilities is constructed. In addition, we propose a new multi-loss strong-constrained optimization strategy, which can facilitate reasonable network optimization and efficient extraction of invariant and discriminative features. Furthermore, a public VIS-LWIR patch dataset and a public SEN1-2 patch dataset are constructed. At the same time, the corresponding experimental benchmarks are established, which are convenient for future research while solving few existing cross-spectral image patch matching datasets. Extensive experiments show that the proposed FIL-Net achieves state-of-the-art performance in three different cross-spectral image patch matching scenarios.

Infrared small target suffers from the lack of intrinsic features, context and samples. Conventional detection methods are usually unable to sufficiently and effectively extract the features of infrared small targets. Therefore, we propose a novel attention-based local contrast learning network (ALCL-Net). Considering the scarcity of intrinsic features of infrared small targets, we propose ResNet32, which enhances the ability to extract infrared small target features and avoids the problem that the target features are overwhelmed by the background features due to too deep network. At the same time, we construct a simplified bilinear interpolation attention module (SBAM), which is used for fusion of hierarchical feature maps. It has fast inference speed and can focus on the feature of the target in the lack of context. Furthermore, local contrast learning (LCL) is introduced, which adopts the local contrast idea of non-deep learning methods. It can alleviate the dependence on dataset samples, thereby improving detection accuracy on datasets with few samples. Compared with the state-of-the-art methods, the proposed ALCL-Net achieves superior performance with an intersection-over-union (IoU) of 0.792 and normalized IoU (nIoU) of 0.771 on the public SIRST dataset.

Deception is a very common phenomenon and its detection can be beneficial to our daily lives. Compared with other deception cues, micro-expression has shown great potential as a promising cue for deception detection. The spotting and recognition of micro-expression from long videos may significantly aid both law enforcement officers and researchers. However, database that contains both micro-expression and macro-expression in long videos is still not publicly available. To facilitate development in this field, we present a new database, Chinese Academy of Sciences Macro-Expressions and Micro-Expressions (CAS(ME)2), which provides both macro-expressions and micro-expressions in two parts (A and B). Part A contains 87 long videos that contain spontaneous macro-expressions and micro-expressions. Part B includes 300 cropped spontaneous macro-expression samples and 57 micro-expression samples. The emotion labels are based on a combination of action units (AUs), self-reported emotion for every facial movement, and the emotion types of emotion-evoking videos. Local Binary Pattern (LBP) was employed for the spotting and recognition of macro-expressions and micro-expressions and the results were reported as a baseline evaluation. The CAS(ME)2database offers both long videos and cropped expression samples, which may aid researchers in developing efficient algorithms for the spotting and recognition of macro-expressions and micro-expressions.

In this paper, we propose a novel model to study the efficiency of detecting latent connection relationships, represented by a given set of graphs, among N users. A subset of active nodes transmit following a common codebook over a multiple access Boolean channel. To maximize the error exponent of the structure detection, we formulate an optimization problem whose objective is to max-minimize the pairwise Chernoff information, and the constraint is a probability simplex due to the users' multiple dependency relationships, which are further shown to have close relationship to the internal connectivity of graphs. Case studies are provided to show certain inherent properties of the optimal solution. In addition, we present a particular case with two equally weighted complementary Paley graphs of prime square order, whose optimal solution for the codebook is proved and the resulting exponent is shown to be O(1/N). The case study demonstrates how the fundamental graph discrepancy property affects the solution to the problem.

In this paper, we propose a novel reservation system to study partition information and its transmission over a noise-free Boolean multiaccess channel. The objective of transmission is not to restore the message, but to partition active users into distinct groups so that they can, subsequently, transmit their messages without collision. We first calculate (by mutual information) the amount of information needed for the partitioning without channel effects, and then propose two different coding schemes to obtain achievable transmission rates over the channel. The first one is the brute force method, where the codebook design is based on centralized source coding; the second method uses random coding, where the codebook is generated randomly and optimal Bayesian decoding is employed to reconstruct the partition. Both methods shed light on the internal structure of the partition problem. A novel formulation is proposed for the random coding scheme, in which a sequence of channel operations and interactions induces a hypergraph. The formulation intuitively describes the transmitted information in terms of a strong coloring of this hypergraph. An extended Fibonacci structure is constructed for the simple, but nontrivial, case with two active users. A comparison between these methods and group testing is conducted to demonstrate the potential of our approaches.

In this paper, we consider the problem of partitioning active users in a manner that facilitates multi-access without collision. The setting is of a noisy, synchronous, Boolean, and multi-access channel, where K active users (out of a total of N users) seek channel access. A solution to the partition problem places each of the N users in one of K groups (or blocks), such that no two active nodes are in the same block. We consider a simple, but non-trivial and illustrative, case of K = 2 active users and study the number of steps T used to solve the partition problem. By random coding and a suboptimal decoding scheme, we show that for any T ≥ (C1+ ξ1) log N, where C1and ξ1are positive constants (independent of N), and where ξ1can be arbitrary small, the partition problem can be solved with error probability Pe(N)→ 0, for large N. Under the same scheme, we also bound T from the other direction, establishing that, for any T ≤ (C2- ξ2) log N, the error probability Pe(N)→ 1 for large N; again, C2and ξ2are constants, and ξ2can be arbitrarily small. These bounds on the number of steps are lower than the tight achievable lower bound in terms of T ≥ (Cg+ ξ) log N for group testing (in which all active users are identified, rather than just partitioned). Thus, partitioning may prove to be a more efficient approach for multi-access than group testing.

In this paper, we formulate a novel problem to quantify the amount of information transferred to partition active users who transmit following a common codebook over noisy Boolean multi-access channels. The objective of transmission is to ultimately let each active user aware of its own group only, not others. To solve the problem, we propose a novel framework by considering the decoding as a process of removing hyperedges of a complete hypergraph. For a particular, but non-trivial, case with two active users, an achievable bound for the defined partition information rate is found by using strong typical set decoding, as well as a large deviation technique for an induced Markov chain.