Event cameras have gained attention in segmentation due to their higher temporal resolution and dynamic range compared to traditional cameras. However, they struggle with issues like lack of color perception and triggering only at motion edges, making it hard to distinguish objects with similar contours or segment spatially continuous objects. Our work aims to address these often overlooked issues. Based on the assumption that various objects exhibit different motion patterns, we believe that embedding the historical motion states of objects into segmented scenes can effectively address these challenges. Inspired by this, we propose the ESS framework ``Know Where You Are From" (KWYAF), which incorporates past motion cues through spatio-temporal propagation embedding. This framework features two core components: the Sequential Motion Encoding Module (SME) and the Event-Based Reliable Region Selection Mechanism (ER²SM). SMEs construct prior motion features through spatio-temporal correlation modeling for boosting final segmentation, while ER²SM adapts to identify high-confidence regions, embedding motion more precisely through local window masks and reliable region selection. A large number of experiments have demonstrated the effectiveness of our proposed framework in terms of both quantity and quality.

Salient object detection (SOD) methods for 2D images have great significance in the field of human-computer interaction (HCI). However, as a common data format in HCI, the SOD research in the form of 3D point cloud data remains limited. Previous works commonly treat this task as point cloud segmentation, which perceives all points in the scene for prediction. However, these methods neglect that SOD is designed to simulate human visual perception where human can only see the surfaces rather than occluded point clouds. Thereby, these methods may fail when meet such situations. This paper aims to solve this problem by approximately simulating the perception paradigm of humans towards 3D scenes. Thus, we propose a framework based on the 3D visual point cloud backbone and its multi-view projection named MSV-PCT. Specifically, instead of relying solely on general point cloud learning frameworks, we additionally introduce multi-sparse-view learning branches to supplement the SOD perception. Furthermore, we propose a novel point cloud edge detection loss function to effectively address artifacts, enabling the accurate segmentation of the edges of salient objects from the background. Finally, to evaluate the generalization of point cloud SOD methods, we introduce a new approach to generate simulated PC-SOD datasets from RGBD-SOD data. Experiments on the simulated datasets show that MSV-PCT achieves better accuracy and robustness.

Fine-grained bird image classification (FBIC) is not only meaningful for endangered bird observation and protection but also a prevalent task for image classification in multimedia processing and computer vision. However, FBIC suffers from several challenges, such as bird molting, complex background, and arbitrary bird posture. To effectively tackle these challenges, we present a novel invariant cues-aware feature concentration Transformer (TransIFC), which learns invariant and core information in bird images. To this end, two novel modules are proposed to leverage the characteristics of bird images, namely, the hierarchy stage feature aggregation (HSFA) module and the feature in feature abstraction (FFA) module. The HSFA module aggregates the multiscale information of bird images by concatenating multilayer features. The FFA module extracts the invariant cues of birds through feature selection based on discrimination scores. Transformer is employed as the backbone to reveal the long-dependent semantic relationships in bird images. Moreover, abundant visualizations are provided to prove the interpretability of the HSFA and FFA modules in TransIFC. Comprehensive experiments demonstrate that TransIFC can achieve state-of-the-art performance on the CUB-200-2011 dataset (91.0%) and the NABirds dataset (90.9%). Finally, extended experiments have been conducted on the Stanford Cars dataset to suggest the potential of generalizing our method on other fine-grained visual classification tasks.

Event cameras are neuromorphic vision sensors that record a scene as sparse and asynchronous event streams. Most event-based methods project events into dense frames and process them using conventional vision models, resulting in high computational complexity. A recent trend is to develop point-based networks that achieve efficient event processing by learning sparse representations. However, existing works may lack robust local information aggregators and effective feature interaction operations, thus limiting their modeling capabilities. To this end, we propose an attention-aware model named Event Voxel Set Transformer (EVSTr) for efficient spatiotemporal representation learning on event streams. It first converts the event stream into voxel sets and then hierarchically aggregates voxel features to obtain robust representations. The core of EVSTr is an event voxel transformer encoder that consists of two well-designed components, including the Multi-Scale Neighbor Embedding Layer (MNEL) for local information aggregation and the Voxel Self-Attention Layer (VSAL) for global feature interaction. Enabling the network to incorporate a long-range temporal structure, we introduce a segment modeling strategy (S2TM) to learn motion patterns from a sequence of segmented voxel sets. The proposed model is evaluated on two recognition tasks, including object classification and action recognition. To provide a convincing model evaluation, we present a new event-based action recognition dataset (NeuroHAR) recorded in challenging scenarios. Comprehensive experiments show that EVSTr achieves state-of-the-art performance while maintaining low model complexity.

Bio-inspired event cameras record a scene as sparse and asynchronous “events” by detecting per-pixel brightness changes. Such cameras show great potential in challenging scene understanding tasks, benefiting from the imaging advantages of high dynamic range and high temporal resolution. Considering the complementarity between event and standard cameras, we propose a multi-modal fusion network (EISNet) to improve the semantic segmentation performance. The key challenges of this topic lie in (i) how to encode event data to represent accurate scene information and (ii) how to fuse multi-modal complementary features by considering the characteristics of two modalities. To solve the first challenge, we propose an Activity-Aware Event Integration Module (AEIM) to convert event data into frame-based representations with high-confidence details via scene activity modeling. To tackle the second challenge, we introduce the Modality Recalibration and Fusion Module (MRFM) to recalibrate modal-specific representations and then aggregate multi-modal features at multiple stages. MRFM learns to generate modal-oriented masks to guide the merging of complementary features, achieving adaptive fusion. Based on these two core designs, our proposed EISNet adopts an encoder-decoder transformer architecture for accurate semantic segmentation using events and images. Experimental results show that our model outperforms state-of-the-art methods by a large margin on event-based semantic segmentation datasets. The code is publicly available athttps://github.com/bochenxie/EISNet.

Head pose estimation (HPE) has been widely used in the fields of human machine interaction, self-driving, and attention estimation. However, existing methods cannot deal with extreme head pose randomness and serious occlusions. To address these challenges, we identify three cues from head images, namely, neighborhood similarities, significant facial changes, and critical minority relationships. To leverage the observed findings, we propose a novel critical minority relationship-aware method based on the Transformer architecture in which the facial part relationships can be learned. Specifically, we design several orientation tokens to explicitly encode the basic orientation regions. Meanwhile, a novel token guide multiloss function is designed to guide the orientation tokens as they learn the desired regional similarities and relationships. We evaluate the proposed method on three challenging benchmark HPE datasets. Experiments show that our method achieves better performance compared with state-of-the-art methods. Our code is publicly available at https://github.com/zc2023/TokenHPE.