Video-based person re-identification (Re-ID) aims to retrieve video sequences of the same person under non-overlapping cameras. Previous methods usually focus on limited views, such as spatial, temporal or spatial-temporal view, which lack of the observations in different feature domains. To capture richer perceptions and extract more comprehensive video representations, in this paper we propose a novel framework named Trigeminal Transformers (TMT) for video-based person Re-ID. More specifically, we design a trigeminal feature extractor to jointly transform raw video data into spatial, temporal and spatial-temporal domain. Besides, inspired by the great success of vision transformer, we introduce the transformer structure for video-based person Re-ID. In our work, three self-view transformers are proposed to exploit the relationships between local features for information enhancement in spatial, temporal and spatial-temporal domains. Moreover, a cross-view transformer is proposed to aggregate the multi-view features for comprehensive video representations. The experimental results indicate that our approach can achieve better performance than other state-of-the-art approaches on public Re-ID benchmarks. We will release the code for model reproduction.
Video-based person re-identification (Re-ID) aims to automatically retrieve video sequences of the same person under non-overlapping cameras. To achieve this goal, it is the key to fully utilize abundant spatial and temporal cues in videos. Existing methods usually focus on the most conspicuous image regions, thus they may easily miss out fine-grained clues due to the person varieties in image sequences. To address above issues, in this paper, we propose a novel Global-guided Reciprocal Learning (GRL) framework for video-based person Re-ID. Specifically, we first propose a Global-guided Correlation Estimation (GCE) to generate feature correlation maps of local features and global features, which help to localize the high- and low-correlation regions for identifying the same person. After that, the discriminative features are disentangled into high-correlation features and low-correlation features under the guidance of the global representations. Moreover, a novel Temporal Reciprocal Learning (TRL) mechanism is designed to sequentially enhance the high-correlation semantic information and accumulate the low-correlation sub-critical clues. Extensive experiments are conducted on three public benchmarks. The experimental results indicate that our approach can achieve better performance than other state-of-the-art approaches. The code is released at https://github.com/flysnowtiger/GRL.
In this paper, we present a new tracking architecture with an encoder-decoder transformer as the key component. The encoder models the global spatio-temporal feature dependencies between target objects and search regions, while the decoder learns a query embedding to predict the spatial positions of the target objects. Our method casts object tracking as a direct bounding box prediction problem, without using any proposals or predefined anchors. With the encoder-decoder transformer, the prediction of objects just uses a simple fully-convolutional network, which estimates the corners of objects directly. The whole method is end-to-end, does not need any postprocessing steps such as cosine window and bounding box smoothing, thus largely simplifying existing tracking pipelines. The proposed tracker achieves state-of-the-art performance on five challenging short-term and long-term benchmarks, while running at real-time speed, being 6x faster than Siam R-CNN. Code and models are open-sourced at https://github.com/researchmm/Stark.
Correlation acts as a critical role in the tracking field, especially in recent popular Siamese-based trackers. The correlation operation is a simple fusion manner to consider the similarity between the template and the search region. However, the correlation operation itself is a local linear matching process, leading to lose semantic information and fall into local optimum easily, which may be the bottleneck of designing high-accuracy tracking algorithms. Is there any better feature fusion method than correlation? To address this issue, inspired by Transformer, this work presents a novel attention-based feature fusion network, which effectively combines the template and search region features solely using attention. Specifically, the proposed method includes an ego-context augment module based on self-attention and a cross-feature augment module based on cross-attention. Finally, we present a Transformer tracking (named TransT) method based on the Siamese-like feature extraction backbone, the designed attention-based fusion mechanism, and the classification and regression head. Experiments show that our TransT achieves very promising results on six challenging datasets, especially on large-scale LaSOT, TrackingNet, and GOT-10k benchmarks. Our tracker runs at approximatively 50 fps on GPU. Code and models are available at https://github.com/chenxin-dlut/TransT.
Existing CNNs-Based RGB-D Salient Object Detection (SOD) networks are all required to be pre-trained on the ImageNet to learn the hierarchy features which can help to provide a good initialization. However, the collection and annotation of large-scale datasets are time-consuming and expensive. In this paper, we utilize Self-Supervised Representation Learning (SSL) to design two pretext tasks: the cross-modal auto-encoder and the depth-contour estimation. Our pretext tasks require only a few and unlabeled RGB-D datasets to perform pre-training, which make the network capture rich semantic contexts as well as reduce the gap between two modalities, thereby providing an effective initialization for the downstream task. In addition, for the inherent problem of cross-modal fusion in RGB-D SOD, we propose a multi-path fusion (MPF) module that splits a single feature fusion into multi-path fusion to achieve an adequate perception of consistent and differential information. The MPF module is general and suitable for both cross-modal and cross-level feature fusion. Extensive experiments on six benchmark RGB-D SOD datasets, our model pre-trained on the RGB-D dataset ($6,335$ without any annotations) can perform favorably against most state-of-the-art RGB-D methods pre-trained on ImageNet ($1,280,000$ with image-level annotations).
In the last few years, image denoising has benefited a lot from the fast development of neural networks. However, the requirement of large amounts of noisy-clean image pairs for supervision limits the wide use of these models. Although there have been a few attempts in training an image denoising model with only single noisy images, existing self-supervised denoising approaches suffer from inefficient network training, loss of useful information, or dependence on noise modeling. In this paper, we present a very simple yet effective method named Neighbor2Neighbor to train an effective image denoising model with only noisy images. Firstly, a random neighbor down-sampler is proposed for the generation of training image pairs. In detail, input and target used to train a network are images down-sampled from the same noisy image, satisfying the requirement that paired pixels of paired images are neighbors and have very similar appearance with each other. Secondly, a denoising network is trained on down-sampled training pairs generated in the first stage, with a proposed regularizer as additional loss for better performance. The proposed Neighbor2Neighbor framework is able to enjoy the progress of state-of-the-art supervised denoising networks in network architecture design. Moreover, it avoids heavy dependence on the assumption of the noise distribution. We explain our approach from a theoretical perspective and further validate it through extensive experiments, including synthetic experiments with different noise distributions in sRGB space and real-world experiments on a denoising benchmark dataset in raw-RGB space.
Image-text matching plays a critical role in bridging the vision and language, and great progress has been made by exploiting the global alignment between image and sentence, or local alignments between regions and words. However, how to make the most of these alignments to infer more accurate matching scores is still underexplored. In this paper, we propose a novel Similarity Graph Reasoning and Attention Filtration (SGRAF) network for image-text matching. Specifically, the vector-based similarity representations are firstly learned to characterize the local and global alignments in a more comprehensive manner, and then the Similarity Graph Reasoning (SGR) module relying on one graph convolutional neural network is introduced to infer relation-aware similarities with both the local and global alignments. The Similarity Attention Filtration (SAF) module is further developed to integrate these alignments effectively by selectively attending on the significant and representative alignments and meanwhile casting aside the interferences of non-meaningful alignments. We demonstrate the superiority of the proposed method with achieving state-of-the-art performances on the Flickr30K and MSCOCO datasets, and the good interpretability of SGR and SAF modules with extensive qualitative experiments and analyses.
Light field data exhibit favorable characteristics conducive to saliency detection. The success of learning-based light field saliency detection is heavily dependent on how a comprehensive dataset can be constructed for higher generalizability of models, how high dimensional light field data can be effectively exploited, and how a flexible model can be designed to achieve versatility for desktop computers and mobile devices. To answer these questions, first we introduce a large-scale dataset to enable versatile applications for RGB, RGB-D and light field saliency detection, containing 102 classes and 4204 samples. Second, we present an asymmetrical two-stream model consisting of the Focal stream and RGB stream. The Focal stream is designed to achieve higher performance on desktop computers and transfer focusness knowledge to the RGB stream, relying on two tailor-made modules. The RGB stream guarantees the flexibility and memory/computation efficiency on mobile devices through three distillation schemes. Experiments demonstrate that our Focal stream achieves state-of-the-arts performance. The RGB stream achieves Top-2 F-measure on DUTLF-V2, which tremendously minimizes the model size by 83% and boosts FPS by 5 times, compared with the best performing method. Furthermore, our proposed distillation schemes are applicable to RGB saliency models, achieving impressive performance gains while ensuring flexibility.
Visual object tracking aims to precisely estimate the bounding box for the given target, which is a challenging problem due to factors such as deformation and occlusion. Many recent trackers adopt the multiple-stage tracking strategy to improve the quality of bounding box estimation. These methods first coarsely locate the target and then refine the initial prediction in the following stages. However, existing approaches still suffer from limited precision, and the coupling of different stages severely restricts the method's transferability. This work proposes a novel, flexible, and accurate refinement module called Alpha-Refine, which can significantly improve the base trackers' prediction quality. By exploring a series of design options, we conclude that the key to successful refinement is extracting and maintaining detailed spatial information as much as possible. Following this principle, Alpha-Refine adopts a pixel-wise correlation, a corner prediction head, and an auxiliary mask head as the core components. We apply Alpha-Refine to six famous base trackers to verify our method's effectiveness: DiMPsuper, DiMP50, ATOM, SiamRPN++, RT-MDNet, and ECO. Comprehensive experiments on TrackingNet, LaSOT, GOT-10K, and VOT2020 benchmarks show that our approach significantly improves the base tracker's performance with little extra latency. Code and pretrained model is available at https://github.com/MasterBin-IIAU/AlphaRefine.