Diffusion models have revitalized the image generation domain, playing crucial roles in both academic research and artistic expression. With the emergence of new diffusion models, assessing the performance of text-to-image models has become increasingly important. Current metrics focus on directly matching the input text with the generated image, but due to cross-modal information asymmetry, this leads to unreliable or incomplete assessment results. Motivated by this, we introduce the Image Regeneration task in this study to assess text-to-image models by tasking the T2I model with generating an image according to the reference image. We use GPT4V to bridge the gap between the reference image and the text input for the T2I model, allowing T2I models to understand image content. This evaluation process is simplified as comparisons between the generated image and the reference image are straightforward. Two regeneration datasets spanning content-diverse and style-diverse evaluation dataset are introduced to evaluate the leading diffusion models currently available. Additionally, we present ImageRepainter framework to enhance the quality of generated images by improving content comprehension via MLLM guided iterative generation and revision. Our comprehensive experiments have showcased the effectiveness of this framework in assessing the generative capabilities of models. By leveraging MLLM, we have demonstrated that a robust T2M can produce images more closely resembling the reference image.

Advances in talking-head animation based on Latent Diffusion Models (LDM) enable the creation of highly realistic, synchronized videos. These fabricated videos are indistinguishable from real ones, increasing the risk of potential misuse for scams, political manipulation, and misinformation. Hence, addressing these ethical concerns has become a pressing issue in AI security. Recent proactive defense studies focused on countering LDM-based models by adding perturbations to portraits. However, these methods are ineffective at protecting reference portraits from advanced image-to-video animation. The limitations are twofold: 1) they fail to prevent images from being manipulated by audio signals, and 2) diffusion-based purification techniques can effectively eliminate protective perturbations. To address these challenges, we propose Silencer, a two-stage method designed to proactively protect the privacy of portraits. First, a nullifying loss is proposed to ignore audio control in talking-head generation. Second, we apply anti-purification loss in LDM to optimize the inverted latent feature to generate robust perturbations. Extensive experiments demonstrate the effectiveness of Silencer in proactively protecting portrait privacy. We hope this work will raise awareness among the AI security community regarding critical ethical issues related to talking-head generation techniques. Code: https://github.com/yuangan/Silencer.

The proliferation of text-to-image diffusion models (T2I DMs) has led to an increased presence of AI-generated images in daily life. However, biased T2I models can generate content with specific tendencies, potentially influencing people’s perceptions. Intentional exploitation of these biases risks conveying misleading information to the public. Current research on bias primarily addresses explicit biases with recognizable visual patterns, such as skin color and gender. This paper introduces a novel form of implicit bias that lacks explicit visual features but can manifest in diverse ways across various semantic contexts. This subtle and versatile nature makes this bias challenging to detect, easy to propagate, and adaptable to a wide range of scenarios. We further propose an implicit bias injection attack framework (IBI-Attacks) against T2I diffusion models by precomputing a general bias direction in the prompt embedding space and adaptively adjusting it based on different inputs. Our attack module can be seamlessly integrated into pre-trained diffusion models in a plug-and-play manner without direct manipulation of user input or model retraining. Extensive experiments validate the effectiveness of our scheme in introducing bias through subtle and diverse modifications while preserving the original semantics. The strong concealment and transferability of our attack across various scenarios further underscore the significance of our approach.

Large Language Models (LLMs) have shown the promising planning capabilities for robotic manipulation, which advances the development of embodied intelligence significantly. However, existing LLM-driven robotic manipulation approaches excel at simple pick-and-place tasks but are insufficient for complex manipulation tasks due to inaccurate procedural knowledge. Besides, for embodied intelligence, equipping a large scale LLM is energy-consuming and inefficient, which affects its real-world application. To address the above problems, we propose Hierarchical Procedural Knowledge Graphs (\textbf{HP-KG}) to enhance LLMs for complex robotic planning while significantly reducing the demand for LLM scale in robotic manipulation. Considering that the complex real-world tasks require multiple steps, and each step is composed of robotic-understandable atomic actions, we design a hierarchical knowledge graph structure to model the relationships between tasks, steps, and actions. This design bridges the gap between human instructions and robotic manipulation actions. To construct HP-KG, we develop an automatic knowledge graph construction framework powered by LLM-based multi-agents, which eliminates costly manual efforts while maintaining high-quality graph structures. The resulting HP-KG encompasses over 40k activity steps across more than 6k household tasks, spanning diverse everyday scenarios. Extensive experiments demonstrate that small scale LLMs (7B) enhanced by our HP-KG significantly improve the planning capabilities, which are stronger than 72B LLMs only. Encouragingly, our approach remains effective on the most powerful GPT-4o model.

Image-based virtual try-on systems, which fit new garments onto human portraits, are gaining research attention. An ideal pipeline should preserve the static features of clothes, such as textures and logos, while also generating the adaptive dynamic clothes elements, e.g., shadows and folds. Previous works fail specifically in generating dynamic clothes features, as they maintain the warped in-shop clothes trivially with predicted an alpha mask by composition. To break the dilemma of over-preserving and textures losses, we propose a novel diffusion-based Product-level virtual try-on pipeline, PLTON, which can preserve the fine details of logos and embroideries while producing realistic clothes shading and wrinkles. The main insights are in three folds: 1) Adaptive Dynamic Rendering. Harnessing the potential of a pre-trained diffusion model as a generative prior, we condition it based on image-based visual features and train a novel dynamic feature extractor. This extractor generates dynamic tokens retaining high-fidelity semantic content, enabling the creation of compellingly authentic shadows and wrinkles in virtual garments. 2) Static Characteristics Transformation. PLTON commences by mapping in-shop clothes to the target pose using a conventional warping network. Thereafter, a high-pass filter extracts an High-Frequency Maps (HF-Map) to scrupulously retain static fabric features. These HF-Maps inform the generation of modulation maps via our static extractor, which are subsequently integrated into a fixed U-net for the synthesis of the final, detailed garment images. 3) Retention Enhancement Strategy. We propose a Two-stage hybrid denoising technique to steer the diffusion process towards accurate spatial layouts and color fidelity, thus enhancing retention of visual information. PLTON is fine-tuned solely with a modestly-sized try-on dataset. Extensive quantitative and qualitative experiments conducted on high-resolution datasets substantiate the superiority of our framework in emulating the complex dynamics found in real clothing scenarios.

Hypothesis inference, a sophisticated cognitive process that allows humans to construct plausible explanations for incomplete observations, is paramount to our ability to make sense of the world around us. Despite the universality of this skill, it remains under-explored within the context of multi-modal AI, which necessitates analyzing observation, recalling information in the mind, and generating explanations. In this work, we propose the Cross-modal Observation hypothesIs iNference task (COIN). Given a textual description of a partially observed event, COIN strives to recall the most probable event from the visual mind (video pool), and infer the subsequent action flow connecting the visual mind event and the observed textural event. To advance the development of this field, we propose a large-scale text-video dataset, Tex-COIN, that contains 39,796 meticulously annotated hypothesis inference examples and auxiliary commonsense knowledge (appearance, clothing, action, etc.) for key video characters. Based on the proposed Tex-COIN dataset, we design a strong baseline, COINNet, which features two perspectives: 1) aligning temporally displaced textual observations with target videos via transformer-based multi-task learning, and 2) inferring the action flow with non-parametric graph-based inference grounded in graph theory. Extensive experiments on the Tex-COIN dataset validate the effectiveness of our COINNet by significantly outperforming the state-of-the-arts.

Federated Learning (FL) is commonly used to collaboratively train models with privacy preservation. In this paper, we found out that the popular diffusion models have introduced a new vulnerability to FL, which brings serious privacy threats. Despite stringent data management measures, attackers can steal massive private data from local clients through multiple Trojans, which control generative behaviors with multiple triggers. We refer to the new task as ${\bf\textit{DataStealing}}$ and demonstrate that the attacker can achieve the purpose based on our proposed Combinatorial Triggers (ComboTs) in a vanilla FL system. However, advanced distance-based FL defenses are still effective in filtering the malicious update according to the distances between each local update. Hence, we propose an Adaptive Scale Critical Parameters (AdaSCP) attack to circumvent the defenses and seamlessly incorporate malicious updates into the global model. Specifically, AdaSCP evaluates the importance of parameters with the gradients in dominant timesteps of the diffusion model. Subsequently, it adaptively seeks the optimal scale factor and magnifies critical parameter updates before uploading to the server. As a result, the malicious update becomes similar to the benign update, making it difficult for distance-based defenses to identify. Extensive experiments reveal the risk of leaking thousands of images in training diffusion models with FL. Moreover, these experiments demonstrate the effectiveness of AdaSCP in defeating advanced distance-based defenses. We hope this work will attract more attention from the FL community to the critical privacy security issues of Diffusion Models. Code: https://github.com/yuangan/DataStealing.

This paper delves into the challenges of achieving scalable and effective multi-object modeling for semi-supervised Video Object Segmentation (VOS). Previous VOS methods decode features with a single positive object, limiting the learning of multi-object representation as they must match and segment each target separately under multi-object scenarios. Additionally, earlier techniques catered to specific application objectives and lacked the flexibility to fulfill different speed-accuracy requirements. To address these problems, we present two innovative approaches, Associating Objects with Transformers (AOT) and Associating Objects with Scalable Transformers (AOST). In pursuing effective multi-object modeling, AOT introduces the IDentification (ID) mechanism to allocate each object a unique identity. This approach enables the network to model the associations among all objects simultaneously, thus facilitating the tracking and segmentation of objects in a single network pass. To address the challenge of inflexible deployment, AOST further integrates scalable long short-term transformers that incorporate scalable supervision and layer-wise ID-based attention. This enables online architecture scalability in VOS for the first time and overcomes ID embeddings' representation limitations. Given the absence of a benchmark for VOS involving densely multi-object annotations, we propose a challenging Video Object Segmentation in the Wild (VOSW) benchmark to validate our approaches. We evaluated various AOT and AOST variants using extensive experiments across VOSW and five commonly used VOS benchmarks, including YouTube-VOS 2018 & 2019 Val, DAVIS-2017 Val & Test, and DAVIS-2016. Our approaches surpass the state-of-the-art competitors and display exceptional efficiency and scalability consistently across all six benchmarks. Moreover, we notably achieved the$\mathbf {1^{st}}$position in the 3 rd Large-scale Video Object Segmentation Challenge. Project page:https://github.com/yoxu515/aot-benchmark.

Mengze Li, Tianbao Wang, Jiahe Xu, Kairong Han, Shengyu Zhang, Zhou Zhao, Jiaxu Miao, Wenqiao Zhang, Shiliang Pu, Fei Wu. Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2023.

Spatio-temporal video grounding aims to localize the aligned visual tube corresponding to a language query. Existing techniques achieve such alignment by exploiting dense boundary and bounding box annotations, which can be prohibitively expensive. To bridge the gap, we investigate the weakly-supervised setting, where models learn from easily accessible video-language data without annotations. We identify that intra-sample spurious correlations among video-language components can be alleviated if the model captures the decomposed structures of video and language data. In this light, we propose a novel framework, namely WINNER, for hierarchical video-text understanding. WINNER first builds the language decomposition tree in a bottom-up manner, upon which the structural attention mechanism and top-down feature backtracking jointly build a multi-modal decomposition tree, permitting a hierarchical understanding of unstructured videos. The multi-modal decomposition tree serves as the basis for multi-hierarchy language-tube matching. A hierarchical contrastive learning objective is proposed to learn the multi-hierarchy correspondence and distinguishment with intra-sample and inter-sample video-text decomposition structures, achieving video-language decomposition structure alignment. Extensive experiments demonstrate the rationality of our design and its effectiveness beyond state-of-the-art weakly supervised methods, even some supervised methods.

Federated Learning (FL) is a distributed learning paradigm that collaboratively learns a global model by multiple clients with data privacy-preserving. Although many FL algorithms have been proposed for classification tasks, few works focus on more challenging semantic segmentation tasks, especially in the class-heterogeneous FL situation. Compared with classification, the issues from heterogeneous FL for semantic segmentation are more severe: (1) Due to the non-IID distribution, different clients may contain inconsistent foreground-background classes, resulting in divergent local updates. (2) Class-heterogeneity for complex dense prediction tasks makes the local optimum of clients farther from the global optimum. In this work, we propose FedSeg, a basic federated learning approach for class-heterogeneous semantic segmentation. We first propose a simple but strong modified cross-entropy loss to correct the local optimization and address the foreground-background inconsistency problem. Based on it, we introduce pixel-level contrastive learning to enforce local pixel embeddings belonging to the global semantic space. Extensive experiments on four semantic segmentation benchmarks (Cityscapes, CamVID, PascalVOC and ADE20k) demonstrate the effectiveness of our FedSeg. We hope this work will attract more attention from the FL community to the challenging semantic segmentation federated learning.

Mengze Li, Tianqi Zhao, Bai Jionghao, Baoyi He, Jiaxu Miao, Wei Ji, Zheqi Lv, Zhou Zhao, Shengyu Zhang, Wenqiao Zhang, Fei Wu. Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing. 2023.

Current methods for open-vocabulary object detection (OVOD) rely on a pre-trained vision-language model (VLM) to acquire the recognition ability. In this paper, we propose a simple yet effective framework to Distill the Knowledge from the VLM to a DETR-like detector, termed DK-DETR. Specifically, we present two ingenious distillation schemes named semantic knowledge distillation (SKD) and relational knowledge distillation (RKD). To utilize the rich knowledge from the VLM systematically, SKD transfers the semantic knowledge explicitly, while RKD exploits implicit relationship information between objects. Furthermore, a distillation branch including a group of auxiliary queries is added to the detector to mitigate the negative effect on base categories. Equipped with SKD and RKD on the distillation branch, DK-DETR improves the detection performance of novel categories significantly and avoids disturbing the detection of base categories. Extensive experiments on LVIS and COCO datasets show that DK-DETR surpasses existing OVOD methods under the setting that the base-category supervision is solely available. The code and models are available at https://github.com/hikvision-research/opera.

Recent advances in semi-supervised semantic segmentation have been heavily reliant on pseudo labeling to compensate for limited labeled data, disregarding the valuable relational knowledge among semantic concepts. To bridge this gap, we devise LogicDiag, a brand new neural-logic semi-supervised learning framework. Our key insight is that conflicts within pseudo labels, identified through symbolic knowledge, can serve as strong yet commonly ignored learning signals. LogicDiag resolves such conflicts via reasoning with logic-induced diagnoses, enabling the recovery of (potentially) erroneous pseudo labels, ultimately alleviating the notorious error accumulation problem. We showcase the practical application of LogicDiag in the data-hungry segmentation scenario, where we formalize the structured abstraction of semantic concepts as a set of logic rules. Extensive experiments on three standard semi-supervised semantic segmentation benchmarks demonstrate the effectiveness and generality of LogicDiag. Moreover, LogicDiag highlights the promising opportunities arising from the systematic integration of symbolic reasoning into the prevalent statistical, neural learning approaches.

Traditional Chinese medicine (TCM) is an interesting research topic in China’s thousands of years of history. With the recent advances in artificial intelligence technology, some researchers have started to focus on learning the TCM prescriptions in a data-driven manner. This involves appropriately recommending a set of herbs based on patients’ symptoms. Most existing herb recommendation models disregard TCM domain knowledge, for example, the interactions between symptoms and herbs and the TCM-informed observations (i.e., TCM formulation of prescriptions). In this paper, we propose a knowledge-guided and TCM-informed approach for herb recommendation. The knowledge used includes path interactions and co-occurrence relationships among symptoms and herbs from a knowledge graph generated from TCM literature and prescriptions. The aforementioned knowledge is used to obtain the discriminative feature vectors of symptoms and herbs via a graph attention network. To increase the ability of herb prediction for the given symptoms, we introduce TCM-informed observations in the prediction layer. We apply our proposed model on a TCM prescription dataset, demonstrating significant improvements over state-of-the-art herb recommendation methods.

We explore the task of language-guided video segmentation (LVS). Previous algorithms mostly adopt 3D CNNs to learn video representation, struggling to capture long-term context and easily suffering from visual-linguistic misalignment. In light of this, we present Locater (local-global context aware Transformer), which augments the Transformer architecture with a finite memory so as to query the entire video with the language expression in an efficient manner. The memory is designed to involve two components - one for persistently preserving global video content, and one for dynamically gathering local temporal context and segmentation history. Based on the memorized local-global context and the particular content of each frame, Locater holistically and flexibly comprehends the expression as an adaptive query vector for each frame. The vector is used to query the corresponding frame for mask generation. The memory also allows Locater to process videos with linear time complexity and constant size memory, while Transformer-style self-attention computation scales quadratically with sequence length. To thoroughly examine the visual grounding capability of LVS models, we contribute a new LVS dataset, A2D-S +, which is built upon A2D-S dataset but poses increased challenges in disambiguating among similar objects. Experiments on three LVS datasets and our A2D-S + show that Locater outperforms previous state-of-the-arts. Further, we won the 1st place in the Referring Video Object Segmentation Track of the 3rd Large-scale Video Object Segmentation Challenge, where Locater served as the foundation for the winning solution.

Scene understanding through pixel-level semantic parsing is one of the main problems in computer vision. Till now, image-based methods and datasets for scene parsing have been well explored. However, the real world is naturally dynamic instead of a static state. Thus, learning to perform video scene parsing is more practical for real-world applications. Considering that few datasets cover an extensive range of scenes and object categories with temporal pixel-level annotations, in this work, we present a large-scale video scene parsing dataset, namely VSPW (Video Scene Parsing in the Wild). To be specific, there are a total of 251,633 frames from 3,536 videos with densely pixel-wise annotations in VSPW, including a large variety of 231 scenes and 124 object categories. Besides, VSPW is densely annotated with a high frame rate of 15 f/s, and over 96% of videos from VSPW have high spatial resolutions from 720P to 4 K. To the best of our knowledge, VSPW is the first attempt to address the challenging video scene parsing task in the wild by considering diverse scenes. Based on our VSPW, we further propose Temporal Attention Blending (TAB) Networks to harness temporal context information for better pixel-level semantic understanding of videos. Extensive experiments on VSPW well demonstrate the superiority of the proposed TAB over other baseline approaches. We hope the new proposed dataset and the explorations in this work can help advance the challenging yet practical video scene parsing task in the future. Both the dataset and the code are available at www.vspwdataset.com.

Mengze Li, Tianbao Wang, Haoyu Zhang, Shengyu Zhang, Zhou Zhao, Jiaxu Miao, Wenqiao Zhang, Wenming Tan, Jin Wang, Peng Wang, Shiliang Pu, Fei Wu. Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2022.

In this paper, we present a new large-scale dataset for the video panoptic segmentation task, which aims to assign semantic classes and track identities to all pixels in a video. As the ground truth for this task is difficult to annotate, previous datasets for video panoptic segmentation are limited by either small scales or the number of scenes. In contrast, our large-scale VIdeo Panoptic Segmentation in the Wild (VIPSeg) dataset provides 3,536 videos and 84,750 frames with pixel-level panoptic annotations, covering a wide range of real-world scenarios and categories. To the best of our knowledge, our VIPSeg is the first attempt to tackle the challenging video panoptic segmentation task in the wild by considering diverse scenarios. Based on VIPSeg, we evaluate existing video panoptic segmentation approaches and propose an efficient and effective clip-based baseline method to analyze our VIPSeg dataset. Our dataset is available at https://github.com/VIPSeg-Dataset/VIPSeg-Dataset/.

Cross-domain weakly supervised object detection (CD-WSOD) aims to adapt the detection model to a novel target domain with easily acquired image-level annotations. How to align the source and target domains is critical to the CDWSOD accuracy. Existing methods usually focus on partial detection components for domain alignment. In contrast, this paper considers that all the detection components are important and proposes a Holistic and Hier-archical Feature Alignment (H2FA) R-CNN. H2FA R-CNN enforces two image-level alignments for the backbone features, as well as two instance-level alignments for the RPN and detection head. This coarse-to-fine aligning hierarchy is in pace with the detection pipeline, i.e., processing the image-level feature and the instance-level features from bottom to top. Importantly, we devise a novel hybrid supervision method for learning two instance-level align-ments. It enables the RPN and detection head to simultane-ously receive weak/full supervision from the target/source domains. Combining all these feature alignments, H2 FA R-CNN effectively mitigates the gap between the source and target domains. Experimental results show that H2 FA R-CNN significantly improves cross-domain object detection accuracy and sets new state of the art on popular benchmarks. Code and pre-trained models are available at https://github.com/XuYunqiu/H2FA_R-CNN.

Video Object Grounding (VOG) is the problem of associating spatial object regions in the video to a descriptive natural language query. This is a challenging vision-language task that necessitates constructing the correct cross-modal correspondence and modeling the appropriate spatio-temporal context of the query video and caption, thereby localizing the specific objects accurately. In this paper, we tackle this task by a novel framework called HiErarchical spatio-tempoRal reasOning (HERO) with contrastive action correspondence. We study the VOG task at two aspects that prior works overlooked: (1) Contrastive Action Correspondence-aware Retrieval. Notice that the fine-grained video semantics (e.g., multiple actions) is not totally aligned with the annotated language query (e.g., single action), we first introduce the weakly-supervised contrastive learning that classifies the video as action-consistent and action-independent frames relying on the video-caption action semantic correspondence. Such a design can build the fine-grained cross-modal correspondence for more accurate subsequent VOG. (2) Hierarchical Spatio-temporal Modeling Improvement. While transformer-based VOG models present their potential in sequential modality (i.e., video and caption) modeling, existing evidence also indicates that the transformer suffers from the issue of the insensitive spatio-temporal locality. Motivated by that, we carefully design the hierarchical reasoning layers to decouple fully connected multi-head attention and remove the redundant interfering correlations. Furthermore, our proposed pyramid and shifted alignment mechanisms are effective to improve the cross-modal information utilization of neighborhood spatial regions and temporal frames. We conducted extensive experiments to show our HERO outperforms existing techniques by achieving significant improvement on two benchmark datasets.

Prevalent semantic segmentation solutions are, in essence, a dense discriminative classifier of p(class|pixel feature). Though straightforward, this de facto paradigm neglects the underlying data distribution p(pixel feature|class), and struggles to identify out-of-distribution data. Going beyond this, we propose GMMSeg, a new family of segmentation models that rely on a dense generative classifier for the joint distribution p(pixel feature,class). For each class, GMMSeg builds Gaussian Mixture Models (GMMs) via Expectation-Maximization (EM), so as to capture class-conditional densities. Meanwhile, the deep dense representation is end-to-end trained in a discriminative manner, i.e., maximizing p(class|pixel feature). This endows GMMSeg with the strengths of both generative and discriminative models. With a variety of segmentation architectures and backbones, GMMSeg outperforms the discriminative counterparts on three closed-set datasets. More impressively, without any modification, GMMSeg even performs well on open-world datasets. We believe this work brings fundamental insights into the related fields.

We focus on the occlusion problem in person re-identification (re-id), which is one of the main challenges in real-world person retrieval scenarios. Previous methods on the occluded re-id problem usually assume that only the probes are occluded, thereby removing occlusions by manually cropping. However, this may not always hold in practice. This article relaxes this assumption and investigates a more general occlusion problem, where both the probe and gallery images could be occluded. The key to this challenging problem is depressing the noise information by identifying bodies and occlusions. We propose to incorporate the pose information into the re-id framework, which benefits the model in three aspects. First, it provides the location of the body. We then design a Pose-Masked Feature Branch to make our model focus on the body region only and filter those noise features brought by occlusions. Second, the estimated pose reveals which body parts are visible, giving us a hint to construct more informative person features. We propose a Pose-Embedded Feature Branch to adaptively re-calibrate channel-wise feature responses based on the visible body parts. Third, in testing, the estimated pose indicates which regions are informative and reliable for both probe and gallery images. Then we explicitly split the extracted spatial feature into parts. Only part features from those commonly visible parts are utilized in the retrieval. To better evaluate the performances of the occluded re-id, we also propose a large-scale data set for the occluded re-id with more than 35 000 images, namely Occluded-DukeMTMC. Extensive experiments show our approach surpasses previous methods on the occluded, partial, and non-occluded re-id data sets.

In this paper, we present a new dataset with the target of advancing the scene parsing task from images to videos. Our dataset aims to perform Video Scene Parsing in the Wild (VSPW), which covers a wide range of real-world scenarios and categories. To be specific, our VSPW is featured from the following aspects: 1) Well-trimmed long-temporal clips. Each video contains a complete shot, lasting around 5 seconds on average. 2) Dense annotation. The pixel-level annotations are provided at a high frame rate of 15 f/s. 3) High resolution. Over 96% of the captured videos are with high spatial resolutions from 720P to 4K. We totally annotate 3,536 videos, including 251,633 frames from 124 categories. To the best of our knowledge, our VSPW is the first attempt to tackle the challenging video scene parsing task in the wild by considering diverse scenarios. Based on VSPW, we design a generic Temporal Context Blending (TCB) network, which can effectively harness long-range contextual information from the past frames to help segment the current one. Extensive experiments show that our TCB network improves both the segmentation performance and temporal stability comparing with image-/video-based state-of-the-art methods. We hope that the scale, diversity, long-temporal, and high frame rate of our VSPW can significantly advance the research of video scene parsing and beyond. The dataset is available at https://www.vspwdataset.com/.

Interactive video object segmentation (iVOS) aims at efficiently harvesting high-quality segmentation masks of the target object in a video with user interactions. Most previous state-of-the-arts tackle the iVOS with two independent networks for conducting user interaction and temporal propagation, respectively, leading to inefficiencies during the inference stage. In this work, we propose a unified framework, named Memory Aggregation Networks (MA-Net), to address the challenging iVOS in a more efficient way. Our MA-Net integrates the interaction and the propagation operations into a single network, which significantly promotes the efficiency of iVOS in the scheme of multi-round interactions. More importantly, we propose a simple yet effective memory aggregation mechanism to record the informative knowledge from the previous interaction rounds, improving the robustness in discovering challenging objects of interest greatly. We conduct extensive experiments on the validation set of DAVIS Challenge 2018 benchmark. In particular, our MA-Net achieves the J@60 score of 76.1% without any bells and whistles, outperforming the state-of-the-arts with more than 2.7%.

Persons are often occluded by various obstacles in person retrieval scenarios. Previous person re-identification (re-id) methods, either overlook this issue or resolve it based on an extreme assumption. To alleviate the occlusion problem, we propose to detect the occluded regions, and explicitly exclude those regions during feature generation and matching. In this paper, we introduce a novel method named Pose-Guided Feature Alignment (PGFA), exploiting pose landmarks to disentangle the useful information from the occlusion noise. During the feature constructing stage, our method utilizes human landmarks to generate attention maps. The generated attention maps indicate if a specific body part is occluded and guide our model to attend to the non-occluded regions. During matching, we explicitly partition the global feature into parts and use the pose landmarks to indicate which partial features belonging to the target person. Only the visible regions are utilized for the retrieval. Besides, we construct a large-scale dataset for the Occluded Person Re-ID problem, namely Occluded-DukeMTMC, which is by far the largest dataset for the Occlusion Person Re-ID. Extensive experiments are conducted on our constructed occluded re-id dataset, two partial re-id datasets, and two commonly used holistic re-id datasets. Our method largely outperforms existing person re-id methods on three occlusion datasets, while remains top performance on two holistic datasets.