Scene graph generation (SGG) aims to understand the visual objects and their semantic relationships from one given image. Until now, lots of SGG datasets with the eyelevel view are released but the SGG dataset with the overhead view is scarcely studied. By contrast to the object occlusion problem in the eyelevel view, which impedes the SGG, the overhead view provides a new perspective that helps to promote the SGG by providing a clear perception of the spatial relationships of objects in the ground scene. To fill in the gap of the overhead view dataset, this paper constructs and releases an aerial image urban scene graph generation (AUG) dataset. Images from the AUG dataset are captured with the low-attitude overhead view. In the AUG dataset, 25,594 objects, 16,970 relationships, and 27,175 attributes are manually annotated. To avoid the local context being overwhelmed in the complex aerial urban scene, this paper proposes one new locality-preserving graph convolutional network (LPG). Different from the traditional graph convolutional network, which has the natural advantage of capturing the global context for SGG, the convolutional layer in the LPG integrates the non-destructive initial features of the objects with dynamically updated neighborhood information to preserve the local context under the premise of mining the global context. To address the problem that there exists an extra-large number of potential object relationship pairs but only a small part of them is meaningful in AUG, we propose the adaptive bounding box scaling factor for potential relationship detection (ABS-PRD) to intelligently prune the meaningless relationship pairs. Extensive experiments on the AUG dataset show that our LPG can significantly outperform the state-of-the-art methods and the effectiveness of the proposed locality-preserving strategy.
Human pose and shape (HPS) estimation with lensless imaging is not only beneficial to privacy protection but also can be used in covert surveillance scenarios due to the small size and simple structure of this device. However, this task presents significant challenges due to the inherent ambiguity of the captured measurements and lacks effective methods for directly estimating human pose and shape from lensless data. In this paper, we propose the first end-to-end framework to recover 3D human poses and shapes from lensless measurements to our knowledge. We specifically design a multi-scale lensless feature decoder to decode the lensless measurements through the optically encoded mask for efficient feature extraction. We also propose a double-head auxiliary supervision mechanism to improve the estimation accuracy of human limb ends. Besides, we establish a lensless imaging system and verify the effectiveness of our method on various datasets acquired by our lensless imaging system.
Inspired by the activity-silent and persistent activity mechanisms in human visual perception biology, we design a Unified Static and Dynamic Network (UniSDNet), to learn the semantic association between the video and text/audio queries in a cross-modal environment for efficient video grounding. For static modeling, we devise a novel residual structure (ResMLP) to boost the global comprehensive interaction between the video segments and queries, achieving more effective semantic enhancement/supplement. For dynamic modeling, we effectively exploit three characteristics of the persistent activity mechanism in our network design for a better video context comprehension. Specifically, we construct a diffusely connected video clip graph on the basis of 2D sparse temporal masking to reflect the "short-term effect" relationship. We innovatively consider the temporal distance and relevance as the joint "auxiliary evidence clues" and design a multi-kernel Temporal Gaussian Filter to expand the context clue into high-dimensional space, simulating the "complex visual perception", and then conduct element level filtering convolution operations on neighbour clip nodes in message passing stage for finally generating and ranking the candidate proposals. Our UniSDNet is applicable to both Natural Language Video Grounding (NLVG) and Spoken Language Video Grounding (SLVG) tasks. Our UniSDNet achieves SOTA performance on three widely used datasets for NLVG, as well as three datasets for SLVG, e.g., reporting new records at 38.88% R@1,IoU@0.7 on ActivityNet Captions and 40.26% R@1,IoU@0.5 on TACoS. To facilitate this field, we collect two new datasets (Charades-STA Speech and TACoS Speech) for SLVG task. Meanwhile, the inference speed of our UniSDNet is 1.56$\times$ faster than the strong multi-query benchmark. Code is available at: https://github.com/xian-sh/UniSDNet.
Channel knowledge map (CKM), which aims to directly reflect the intrinsic channel properties of the local wireless environment, is a novel technique for achieving environmentaware communication. In this paper, to alleviate the large training overhead in millimeter wave (mmWave) beam alignment, an environment-aware and training-free beam alignment prototype is established based on a typical CKM, termed beam index map (BIM). To this end, a general CKM construction method is first presented, and an indoor BIM is constructed offline to learn the candidate transmit and receive beam index pairs for each grid in the experimental area. Furthermore, based on the location information of the receiver (or the dynamic obstacles) from the ultra-wide band (UWB) positioning system, the established BIM is used to achieve training-free beam alignment by directly providing the beam indexes for the transmitter and receiver. Three typical scenarios are considered in the experiment, including quasi-static environment with line-of-sight (LoS) link, quasistatic environment without LoS link and dynamic environment. Besides, the receiver orientation measured from the gyroscope is also used to help CKM predict more accurate beam indexes. The experiment results show that compared with the benchmark location-based beam alignment strategy, the CKM-based beam alignment strategy can achieve much higher received power, which is close to that achieved by exhaustive beam search, but with significantly reduced training overhead.
Video Motion Magnification (VMM) aims to reveal subtle and imperceptible motion information of objects in the macroscopic world. Prior methods directly model the motion field from the Eulerian perspective by Representation Learning that separates shape and texture or Multi-domain Learning from phase fluctuations. Inspired by the frequency spectrum, we observe that the low-frequency components with stable energy always possess spatial structure and less noise, making them suitable for modeling the subtle motion field. To this end, we present FD4MM, a new paradigm of Frequency Decoupling for Motion Magnification with a Multi-level Isomorphic Architecture to capture multi-level high-frequency details and a stable low-frequency structure (motion field) in video space. Since high-frequency details and subtle motions are susceptible to information degradation due to their inherent subtlety and unavoidable external interference from noise, we carefully design Sparse High/Low-pass Filters to enhance the integrity of details and motion structures, and a Sparse Frequency Mixer to promote seamless recoupling. Besides, we innovatively design a contrastive regularization for this task to strengthen the model's ability to discriminate irrelevant features, reducing undesired motion magnification. Extensive experiments on both Real-world and Synthetic Datasets show that our FD4MM outperforms SOTA methods. Meanwhile, FD4MM reduces FLOPs by 1.63$\times$ and boosts inference speed by 1.68$\times$ than the latest method. Our code is available at https://github.com/Jiafei127/FD4MM.
Micro-action is an imperceptible non-verbal behaviour characterised by low-intensity movement. It offers insights into the feelings and intentions of individuals and is important for human-oriented applications such as emotion recognition and psychological assessment. However, the identification, differentiation, and understanding of micro-actions pose challenges due to the imperceptible and inaccessible nature of these subtle human behaviors in everyday life. In this study, we innovatively collect a new micro-action dataset designated as Micro-action-52 (MA-52), and propose a benchmark named micro-action network (MANet) for micro-action recognition (MAR) task. Uniquely, MA-52 provides the whole-body perspective including gestures, upper- and lower-limb movements, attempting to reveal comprehensive micro-action cues. In detail, MA-52 contains 52 micro-action categories along with seven body part labels, and encompasses a full array of realistic and natural micro-actions, accounting for 205 participants and 22,422 video instances collated from the psychological interviews. Based on the proposed dataset, we assess MANet and other nine prevalent action recognition methods. MANet incorporates squeeze-and excitation (SE) and temporal shift module (TSM) into the ResNet architecture for modeling the spatiotemporal characteristics of micro-actions. Then a joint-embedding loss is designed for semantic matching between video and action labels; the loss is used to better distinguish between visually similar yet distinct micro-action categories. The extended application in emotion recognition has demonstrated one of the important values of our proposed dataset and method. In the future, further exploration of human behaviour, emotion, and psychological assessment will be conducted in depth. The dataset and source code are released at https://github.com/VUT-HFUT/Micro-Action.
Visual Question Answering (VQA) is a challenging task of predicting the answer to a question about the content of an image. It requires deep understanding of both the textual question and visual image. Prior works directly evaluate the answering models by simply calculating the accuracy of the predicted answers. However, the inner reasoning behind the prediction is disregarded in such a "black box" system, and we do not even know if one can trust the predictions. In some cases, the models still get the correct answers even when they focus on irrelevant visual regions or textual tokens, which makes the models unreliable and illogical. To generate both visual and textual rationales next to the predicted answer to the given image/question pair, we propose Convincing Rationales for VQA, CRVQA. Considering the extra annotations brought by the new outputs, {CRVQA} is trained and evaluated by samples converted from some existing VQA datasets and their visual labels. The extensive experiments demonstrate that the visual and textual rationales support the prediction of the answers, and further improve the accuracy. Furthermore, {CRVQA} achieves competitive performance on generic VQA datatsets in the zero-shot evaluation setting. The dataset and source code will be released under https://github.com/lik1996/CRVQA2024.
Dual-lens super-resolution (SR) is a practical scenario for reference (Ref) based SR by utilizing the telephoto image (Ref) to assist the super-resolution of the low-resolution wide-angle image (LR input). Different from general RefSR, the Ref in dual-lens SR only covers the overlapped field of view (FoV) area. However, current dual-lens SR methods rarely utilize these specific characteristics and directly perform dense matching between the LR input and Ref. Due to the resolution gap between LR and Ref, the matching may miss the best-matched candidate and destroy the consistent structures in the overlapped FoV area. Different from them, we propose to first align the Ref with the center region (namely the overlapped FoV area) of the LR input by combining global warping and local warping to make the aligned Ref be sharp and consistent. Then, we formulate the aligned Ref and LR center as value-key pairs, and the corner region of the LR is formulated as queries. In this way, we propose a kernel-free matching strategy by matching between the LR-corner (query) and LR-center (key) regions, and the corresponding aligned Ref (value) can be warped to the corner region of the target. Our kernel-free matching strategy avoids the resolution gap between LR and Ref, which makes our network have better generalization ability. In addition, we construct a DuSR-Real dataset with (LR, Ref, HR) triples, where the LR and HR are well aligned. Experiments on three datasets demonstrate that our method outperforms the second-best method by a large margin. Our code and dataset are available at https://github.com/ZifanCui/KeDuSR.
Deep learning-based drug response prediction (DRP) methods can accelerate the drug discovery process and reduce R\&D costs. Although the mainstream methods achieve high accuracy in predicting response regression values, the regression-aware representations of these methods are fragmented and fail to capture the continuity of the sample order. This phenomenon leads to models optimized to sub-optimal solution spaces, reducing generalization ability and may result in significant wasted costs in the drug discovery phase. In this paper, we propose \MN, a contrastive learning framework with natural language supervision for the DRP. The \MN~converts regression labels into text, which is merged with the captions text of the drug response as a second modality of the samples compared to the traditional modalities (graph, sequence). In each batch, two modalities of one sample are considered positive pairs and the other pairs are considered negative pairs. At the same time, in order to enhance the continuous representation capability of the numerical text, a common-sense numerical knowledge graph is introduced. We validated several hundred thousand samples from the Genomics of Drug Sensitivity in Cancer dataset, observing the average improvement of the DRP method ranges from 7.8\% to 31.4\% with the application of our framework. The experiments prove that the \MN~effectively constrains the samples to a continuous distribution in the representation space, and achieves impressive prediction performance with only a few epochs of fine-tuning after pre-training. The code is available at: \url{https://gitee.com/xiaoyibang/clipdrug.git}.
3D human generation is increasingly significant in various applications. However, the direct use of 2D generative methods in 3D generation often results in significant loss of local details, while methods that reconstruct geometry from generated images struggle with global view consistency. In this work, we introduce Joint2Human, a novel method that leverages 2D diffusion models to generate detailed 3D human geometry directly, ensuring both global structure and local details. To achieve this, we employ the Fourier occupancy field (FOF) representation, enabling the direct production of 3D shapes as preliminary results using 2D generative models. With the proposed high-frequency enhancer and the multi-view recarving strategy, our method can seamlessly integrate the details from different views into a uniform global shape.To better utilize the 3D human prior and enhance control over the generated geometry, we introduce a compact spherical embedding of 3D joints. This allows for effective application of pose guidance during the generation process. Additionally, our method is capable of generating 3D humans guided by textual inputs. Our experimental results demonstrate the capability of our method to ensure global structure, local details, high resolution, and low computational cost, simultaneously. More results and code can be found on our project page at http://cic.tju.edu.cn/faculty/likun/projects/Joint2Human.