Customized video generation aims to generate high-quality videos guided by text prompts and subject's reference images. However, since it is only trained on static images, the fine-tuning process of subject learning disrupts abilities of video diffusion models (VDMs) to combine concepts and generate motions. To restore these abilities, some methods use additional video similar to the prompt to fine-tune or guide the model. This requires frequent changes of guiding videos and even re-tuning of the model when generating different motions, which is very inconvenient for users. In this paper, we propose CustomCrafter, a novel framework that preserves the model's motion generation and conceptual combination abilities without additional video and fine-tuning to recovery. For preserving conceptual combination ability, we design a plug-and-play module to update few parameters in VDMs, enhancing the model's ability to capture the appearance details and the ability of concept combinations for new subjects. For motion generation, we observed that VDMs tend to restore the motion of video in the early stage of denoising, while focusing on the recovery of subject details in the later stage. Therefore, we propose Dynamic Weighted Video Sampling Strategy. Using the pluggability of our subject learning modules, we reduce the impact of this module on motion generation in the early stage of denoising, preserving the ability to generate motion of VDMs. In the later stage of denoising, we restore this module to repair the appearance details of the specified subject, thereby ensuring the fidelity of the subject's appearance. Experimental results show that our method has a significant improvement compared to previous methods.

With the rapid proliferation of 3D devices and the shortage of 3D content, stereo conversion is attracting increasing attention. Recent works introduce pretrained Diffusion Models (DMs) into this task. However, due to the scarcity of large-scale training data and comprehensive benchmarks, the optimal methodologies for employing DMs in stereo conversion and the accurate evaluation of stereo effects remain largely unexplored. In this work, we introduce the Mono2Stereo dataset, providing high-quality training data and benchmark to support in-depth exploration of stereo conversion. With this dataset, we conduct an empirical study that yields two primary findings. 1) The differences between the left and right views are subtle, yet existing metrics consider overall pixels, failing to concentrate on regions critical to stereo effects. 2) Mainstream methods adopt either one-stage left-to-right generation or warp-and-inpaint pipeline, facing challenges of degraded stereo effect and image distortion respectively. Based on these findings, we introduce a new evaluation metric, Stereo Intersection-over-Union, which prioritizes disparity and achieves a high correlation with human judgments on stereo effect. Moreover, we propose a strong baseline model, harmonizing the stereo effect and image quality simultaneously, and notably surpassing current mainstream methods. Our code and data will be open-sourced to promote further research in stereo conversion. Our models are available at mono2stereo-bench.github.io.

The research focus of GUI agents is shifting from text-dependent to pure-vision-based approaches, which, though promising, prioritize comprehensive pre-training data collection while neglecting contextual modeling challenges. We probe the characteristics of element and history contextual modeling in GUI agent and summarize: 1) the high-density and loose-relation of element context highlight the existence of many unrelated elements and their negative influence; 2) the high redundancy of history context reveals the inefficient history modeling in current GUI agents. In this work, we propose a context-aware simplification framework for building an efficient and effective GUI Agent, termed SimpAgent. To mitigate potential interference from numerous unrelated elements, we introduce a masking-based element pruning method that circumvents the intractable relation modeling through an efficient masking mechanism. To reduce the redundancy in historical information, we devise a consistency-guided history compression module, which enhances implicit LLM-based compression through innovative explicit guidance, achieving an optimal balance between performance and efficiency. With the above components, SimpAgent reduces 27% FLOPs and achieves superior GUI navigation performances. Comprehensive navigation experiments across diverse web and mobile environments demonstrate the effectiveness and potential of our agent.

Rectified-flow-based diffusion transformers like FLUX and OpenSora have demonstrated outstanding performance in the field of image and video generation. Despite their robust generative capabilities, these models often struggle with inversion inaccuracies, which could further limit their effectiveness in downstream tasks such as image and video editing. To address this issue, we propose RF-Solver, a novel training-free sampler that effectively enhances inversion precision by mitigating the errors in the ODE-solving process of rectified flow. Specifically, we derive the exact formulation of the rectified flow ODE and apply the high-order Taylor expansion to estimate its nonlinear components, significantly enhancing the precision of ODE solutions at each timestep. Building upon RF-Solver, we further propose RF-Edit, a general feature-sharing-based framework for image and video editing. By incorporating self-attention features from the inversion process into the editing process, RF-Edit effectively preserves the structural information of the source image or video while achieving high-quality editing results. Our approach is compatible with any pre-trained rectified-flow-based models for image and video tasks, requiring no additional training or optimization. Extensive experiments across generation, inversion, and editing tasks in both image and video modalities demonstrate the superiority and versatility of our method. The source code is available at https://github.com/wangjiangshan0725/RF-Solver-Edit.

Recent advances in Large Multi-modal Models (LMMs) have demonstrated their remarkable success as general-purpose multi-modal assistants, with particular focuses on holistic image- and video-language understanding. Conversely, less attention has been given to scaling fine-grained pixel-level understanding capabilities, where the models are expected to realize pixel-level alignment between visual signals and language semantics. Some previous studies have applied LMMs to related tasks such as region-level captioning and referring expression segmentation. However, these models are limited to performing either referring or segmentation tasks independently and fail to integrate these fine-grained perception capabilities into visual reasoning. To bridge this gap, we propose UniPixel, a large multi-modal model capable of flexibly comprehending visual prompt inputs and generating mask-grounded responses. Our model distinguishes itself by seamlessly integrating pixel-level perception with general visual understanding capabilities. Specifically, UniPixel processes visual prompts and generates relevant masks on demand, and performs subsequent reasoning conditioning on these intermediate pointers during inference, thereby enabling fine-grained pixel-level reasoning. The effectiveness of our approach has been verified on 10 benchmarks across a diverse set of tasks, including pixel-level referring/segmentation and object-centric understanding in images/videos. A novel PixelQA task that jointly requires referring, segmentation, and question answering is also designed to verify the flexibility of our method.

Weakly-Supervised Temporal Action Localization (WSTAL) aims to localize and classify action instances in long untrimmed videos with only video-level category labels as supervision. A critical challenge of WSTAL is the large gap between video-level supervision and unavailable snippet-level supervision. Prevailing methods typically assign pseudo labels to snippets, but these methods suffer from significant noise caused by the pseudo snippet-level labels. In this work, we address the WSTAL from a novel category exclusion perspective, which gradually enhances the snippet-level supervision to bridge the gap. Our proposed Progressive Complementary Learning (ProCL) is inspired by the fact that, video-level labels precisely indicate the categories that all snippets surely do not belong to, which is ignored by previous works. Accordingly, we first exclude these surely non-existent categories by the deterministic complementary learning. And then, we introduce the entropy-based pseudo complementary learning that is able to exclude more categories for snippets of less ambiguity. Furthermore, for the remaining ambiguous snippets, we attempt to reduce the ambiguity by distinguishing foreground actions from the background. Extensive experimental results show that our method achieves new state-of-the-art performance on THUMOS14, ActivityNet1.3, and MultiTHUMOS benchmarks.

The incredible generative ability of large-scale text-to-image (T2I) models has demonstrated strong power of learning complex structures and meaningful semantics. However, relying solely on text prompts cannot fully take advantage of the knowledge learned by the model, especially when flexible and accurate controlling (e.g., structure and color) is needed. In this paper, we aim to ``dig out" the capabilities that T2I models have implicitly learned, and then explicitly use them to control the generation more granularly. Specifically, we propose to learn low-cost T2I-Adapters to align internal knowledge in T2I models with external control signals, while freezing the original large T2I models. In this way, we can train various adapters according to different conditions, achieving rich control and editing effects in the color and structure of the generation results. Further, the proposed T2I-Adapters have attractive properties of practical value, such as composability and generalization ability. Extensive experiments demonstrate that our T2I-Adapter has promising generation quality and a wide range of applications. Our code is available at https://github.com/TencentARC/T2I-Adapter.

Controllable spherical panoramic image generation holds substantial applicative potential across a variety of domains. However, it remains a challenging task due to the inherent spherical distortion and geometry characteristics, resulting in low-quality content generation. In this paper, we introduce a novel framework of SphereDiffusion to address these unique challenges, for better generating high-quality and precisely controllable spherical panoramic images. For the spherical distortion characteristic, we embed the semantics of the distorted object with text encoding, then explicitly construct the relationship with text-object correspondence to better use the pre-trained knowledge of the planar images. Meanwhile, we employ a deformable technique to mitigate the semantic deviation in latent space caused by spherical distortion. For the spherical geometry characteristic, in virtue of spherical rotation invariance, we improve the data diversity and optimization objectives in the training process, enabling the model to better learn the spherical geometry characteristic. Furthermore, we enhance the denoising process of the diffusion model, enabling it to effectively use the learned geometric characteristic to ensure the boundary continuity of the generated images. With these specific techniques, experiments on Structured3D dataset show that SphereDiffusion significantly improves the quality of controllable spherical image generation and relatively reduces around 35% FID on average.

Dominant dual-encoder models enable efficient image-text retrieval but suffer from limited accuracy, while the cross-encoder models offer higher accuracy at the expense of efficiency. Distilling cross-modality matching knowledge from cross-encoder to dual-encoder provides a natural approach to harness their strengths. Thus, we investigate the following valuable question: how to make cross-encoder a good teacher for dual-encoder? Our findings are threefold: (1) Cross-modal similarity score distribution of cross-encoder is more concentrated, while the result of dual-encoder is nearly normal, making vanilla logit distillation less effective. However, ranking distillation remains practical, as it is not affected by the score distribution. (2) Only the relative order between hard negatives conveys valid knowledge, while the order information between easy negatives has little significance. (3) Maintaining the coordination between distillation loss and dual-encoder training loss is beneficial for knowledge transfer. Based on these findings, we propose a novel Contrastive Partial Ranking Distillation (CPRD) method, which implements the objective of mimicking relative order between hard negative samples with contrastive learning. This approach coordinates with the training of the dual-encoder, effectively transferring valid knowledge from the cross-encoder to the dual-encoder. Extensive experiments on image-text retrieval and ranking tasks show that our method surpasses other distillation methods and significantly improves the accuracy of dual-encoder.

Recent advances in text-to-image generation have made remarkable progress in synthesizing realistic human photos conditioned on given text prompts. However, existing per-sonalized generation methods cannot simultaneously sat-isfy the requirements of high efficiency, promising identity (ID) fidelity, and flexible text controllability. In this work, we introduce PhotoMaker, an efficient personalized text-to-image generation method, which mainly encodes an arbitrary number of input ID images into a stack ID embed-ding for preserving ID information. Such an embedding, serving as a unified ID representation, can not only encap-sulate the characteristics of the same input ID comprehen-sively, but also accommodate the characteristics of differ-ent IDs for subsequent integration. This paves the way for more intriguing and practically valuable applications. Be-sides, to drive the training of our PhotoMaker, we propose an ID-oriented data construction pipeline to assemble the training data. Under the nourishment of the dataset constructed through the proposed pipeline, our PhotoMaker demonstrates better ID preservation ability than test-time fine-tuning based methods, yet provides significant speed improvements, high-quality generation results, strong gen-eralization capabilities, and a wide range of applications.

Incorporating a customized object into image generation presents an attractive feature in text-to-image (T2I) generation. Some methods finetune T2I models for each object individually at test-time, which tend to be overfitted and time-consuming. Others train an extra encoder to extract object visual information for customization efficiently but struggle to preserve the object's identity. To address these limitations, we present CustomNet, a unified encoder-based object customization framework that explicitly incorporates 3D novel view synthesis capabilities into the customization process. This integration facilitates the adjustment of spatial positions and viewpoints, producing diverse outputs while effectively preserving the object's identity. To train our model effectively, we propose a dataset construction pipeline to better handle real-world objects and complex backgrounds. Additionally, we introduce delicate designs that enable location control and flexible background control through textual descriptions or user-defined backgrounds. Our method allows for object customization without the need of test-time optimization, providing simultaneous control over viewpoints, location, and text. Experimental results show that our method outperforms other customization methods regarding identity preservation, diversity, and harmony. Codes are available at https://github.com/TencentARC/CustomNet.

Recent advances in Video Large Language Models (Video-LLMs) have demonstrated their great potential in general-purpose video understanding. To verify the significance of these models, a number of benchmarks have been proposed to diagnose their capabilities in different scenarios. However, existing benchmarks merely evaluate models through video-level question-answering, lacking fine-grained event-level assessment and task diversity. To fill this gap, we introduce E.T. Bench (Event-Level & Time-Sensitive Video Understanding Benchmark), a large-scale and high-quality benchmark for open-ended event-level video understanding. Categorized within a 3-level task taxonomy, E.T. Bench encompasses 7.3K samples under 12 tasks with 7K videos (251.4h total length) under 8 domains, providing comprehensive evaluations. We extensively evaluated 8 Image-LLMs and 12 Video-LLMs on our benchmark, and the results reveal that state-of-the-art models for coarse-level (video-level) understanding struggle to solve our fine-grained tasks, e.g., grounding event-of-interests within videos, largely due to the short video context length, improper time representations, and lack of multi-event training data. Focusing on these issues, we further propose a strong baseline model, E.T. Chat, together with an instruction-tuning dataset E.T. Instruct 164K tailored for fine-grained event-level understanding. Our simple but effective solution demonstrates superior performance in multiple scenarios.

Self-supervised learning (SSL) has recently achieved great success in mining the user-item interactions for collaborative filtering. As a major paradigm, contrastive learning (CL) based SSL helps address data sparsity in Web platforms by contrasting the embeddings between raw and augmented data. However, existing CL-based methods mostly focus on contrasting in a batch-wise way, failing to exploit potential regularity in the feature dimension. This leads to redundant solutions during the representation learning of users and items. In this work, we investigate how to employ both batch-wise CL (BCL) and feature-wise CL (FCL) for recommendation. We theoretically analyze the relation between BCL and FCL, and find that combining BCL and FCL helps eliminate redundant solutions but never misses an optimal solution. We propose a dual contrastive learning recommendation framework---RecDCL. In RecDCL, the FCL objective is designed to eliminate redundant solutions on user-item positive pairs and to optimize the uniform distributions within users and items using a polynomial kernel for driving the representations to be orthogonal; The BCL objective is utilized to generate contrastive embeddings on output vectors for enhancing the robustness of the representations. Extensive experiments on four widely-used benchmarks and one industry dataset demonstrate that RecDCL can consistently outperform the state-of-the-art GNNs-based and SSL-based models (with an improvement of up to 5.65% in terms of Recall@20). The source code is publicly available https://github.com/THUDM/RecDCL

Previous work for video captioning aims to objectively describe the video content but the captions lack human interest and attractiveness, limiting its practical application scenarios. The intention of video title generation (video titling) is to produce attractive titles, but there is a lack of benchmarks. This work offers CREATE, the first large-scale Chinese shoRt vidEo retrievAl and Title gEneration dataset, to assist research and applications in video titling, video captioning, and video retrieval in Chinese. CREATE comprises a high-quality labeled 210 K dataset and two web-scale 3 M and 10 M pre-training datasets, covering 51 categories, 50K+ tags, 537K+ manually annotated titles and captions, and 10M+ short videos with original video information. This work presents ACTEr, a unique Attractiveness-Consensus-based Title Evaluation, to objectively evaluate the quality of video title generation. This metric measures the semantic correlation between the candidate (model-generated title) and references (manual-labeled titles) and introduces attractive consensus weights to assess the attractiveness and relevance of the video title. Accordingly, this work proposes a novel multi-modal ALignment WIth Generation model, ALWIG, as one strong baseline to aid future model development. With the help of a tag-driven video-text alignment module and a GPT-based generation module, this model achieves video titling, captioning, and retrieval simultaneously. We believe that the release of the CREATE dataset, ACTEr metric, and ALWIG model will encourage in-depth research on the analysis and creation of Chinese short videos.

Video captioning evaluation aims at assessing the semantic consistency between video and candidate text, which should include measurement from two aspects: faithfulness (whether the information conveyed by candidate is correct w.r.t. video) and comprehensiveness (whether the main video content is covered by candidate). However, previous approaches have difficulty in evaluating faithfulness and comprehensiveness due to heavy reliance on references or heterogeneous of visual and textual data. In this paper, we propose a vision-involved evaluation metric based on a novel DuAl-Reconstruction Transformer, named DARTScore. DARTScore formulates the caption evaluation task as a dual-reconstruction problem to evaluate both faithfulness and comprehensiveness explicitly. Since the word in a candidate is usually related to several frames, DARTScore adaptively collects relevant frames to reconstruct the word and computes the reconstruction accuracy as faithfulness to inherently reflect whether the word information is contained in the video. In the inversive way, DARTScore reconstructs each frame with relevant words to evaluate comprehensiveness. By integrating fine-grained bidirectional reconstruction accuracies, DARTScore drills into each word in candidate and each frame in video to fully evaluate the semantic consistency. Furthermore, we collect and annotate two Chinese datasets with a large domain gap, named CRAETE-EVAL and VATEX-ZH-EVAL, to systematically evaluate existing metrics and fill the blank of Chinese video captioning evaluation. Experimental results show that DARTScore achieves higher correlation with human judgments, has lower reference reliance, and generalizes well to data from different domains.

Recently, molecular data mining has attracted a lot of attention owing to its great application potential in material and drug discovery. However, this mining task faces a challenge posed by the scarcity of labeled molecular graphs. To overcome this challenge, we introduce a novel data augmentation and a semi-supervised confidence-aware consistency regularization training framework for molecular property prediction. The core of our framework is a data augmentation strategy on molecular graphs, named DropConn (Dropout Connection). DropConn generates pseudo molecular graphs by softening the hard connections of chemical bonds (as edges), where the soft weights are calculated from edge features so that the adaptive interactions between different atoms can be incorporated. Besides, to enhance the model's generalization ability, a consistency regularization training strategy is proposed to take full advantage of massive unlabeled data. Furthermore, DropConn can serve as a plugin that can be seamlessly added to many existing models. Extensive experiments under both non-pre-training setting and fine-tuning setting demonstrate that DropConn can obtain superior performance (up to 8.22%) over state-of-the-art methods on molecular property prediction tasks. The code is available athttps://github.com/THUDM/DropConn.

Vision-language alignment learning for video-text retrieval arouses a lot of attention in recent years. Most of the existing methods either transfer the knowledge of image-text pretraining model to video-text retrieval task without fully exploring the multi-modal information of videos, or simply fuse multi-modal features in a brute force manner without explicit guidance. In this paper, we integrate multi-modal information in an explicit manner by tagging, and use the tags as the anchors for better video-text alignment. Various pretrained experts are utilized for extracting the information of multiple modalities, including object, person, motion, audio, etc. To take full advantage of these information, we propose the TABLE (TAgging Before aLignmEnt) network, which consists of a visual encoder, a tag encoder, a text encoder, and a tag-guiding cross-modal encoder for jointly encoding multi-frame visual features and multi-modal tags information. Furthermore, to strengthen the interaction between video and text, we build a joint cross-modal encoder with the triplet input of [vision, tag, text] and perform two additional supervised tasks, Video Text Matching (VTM) and Masked Language Modeling (MLM). Extensive experimental results demonstrate that the TABLE model is capable of achieving State-Of-The-Art (SOTA) performance on various video-text retrieval benchmarks, including MSR-VTT, MSVD, LSMDC and DiDeMo.

Despite that convolution neural networks (CNN) have recently demonstrated high-quality reconstruction for video super-resolution (VSR), efficiently training competitive VSR models remains a challenging problem. It usually takes an order of magnitude more time than training their counterpart image models, leading to long research cycles. Existing VSR methods typically train models with fixed spatial and temporal sizes from beginning to end. The fixed sizes are usually set to large values for good performance, resulting to slow training. However, is such a rigid training strategy necessary for VSR? In this work, we show that it is possible to gradually train video models from small to large spatial/temporal sizes, \ie, in an easy-to-hard manner. In particular, the whole training is divided into several stages and the earlier stage has smaller training spatial shape. Inside each stage, the temporal size also varies from short to long while the spatial size remains unchanged. Training is accelerated by such a multigrid training strategy, as most of computation is performed on smaller spatial and shorter temporal shapes. For further acceleration with GPU parallelization, we also investigate the large minibatch training without the loss in accuracy. Extensive experiments demonstrate that our method is capable of largely speeding up training (up to $6.2\times$ speedup in wall-clock training time) without performance drop for various VSR models.

Dominant pre-training works for image-text retrieval adopt “dual-encoder” architecture to enable high efficiency, where two encoders are used to extract image and text representations and contrastive learning is employed for global alignment. However, coarse-grained global alignment ignores detailed semantic associations between image and text. In this work, we propose a novel proxy task, named Visual-Language Error Modeling (ViLEM), to inject detailed image-text association into “dual-encoder” model by “proofreading” each word in the text against the corresponding image. Specifically, we first edit the image-paired text to automatically generate diverse plausible negative texts with pre-trained language models. ViLEM then enforces the model to discriminate the correctness of each word in the plausible negative texts and further correct the wrong words via resorting to image information. Further-more, we propose a multi-granularity interaction framework to perform ViLEM via interacting text features with both global and local image features, which associates local text semantics with both high-level visual context and multi-level local visual information. Our method surpasses state-of-the-art “dual-encoder” methods by a large margin on the image-text retrieval task and significantly improves discriminativeness to local textual semantics. Our model can also generalize well to video-text retrieval.

Recently, diffusion models have achieved great success in image synthesis. However, when it comes to the layout-to-image generation where an image often has a complex scene of multiple objects, how to make strong control over both the global layout map and each detailed object remains a challenging task. In this paper, we propose a diffusion model named LayoutDiffusion that can obtain higher generation quality and greater controllability than the previous works. To overcome the difficult multimodal fusion of image and layout, we propose to construct a structural image patch with region information and transform the patched image into a special layout to fuse with the normal layout in a unified form. Moreover, Layout Fusion Module (LFM) and Object-aware Cross Attention (OaCA) are proposed to model the relationship among multiple objects and designed to be object-aware and position-sensitive, allowing for precisely controlling the spatial related information. Extensive experiments show that our LayoutDiffusion out-performs the previous SOTA methods on FID, CAS by relatively 46.35%,26.70% on COCO-stuff and 44.29%,41.82% on VG. Code is available at https://github.com/ZGCTroy/LayoutDiffusion.

The scene graph generation (SGG) task has attracted increasing attention in recent years. The goal of SGG is to predict relations between pairs of objects within an image. Due to the long-tailed distribution of the dataset annotations, the performance of SGG is still far from satisfactory. To address the long-tailed problem, existing methods try various ways to conduct unbiased learning. However, we argue that the essence of the long-tailed problem in SGG is that the classifier is seriously affected by the long-tailed data. To handle this issue, we propose a novel network named ERBNet, which contains a relation feature fusion (RFF) encoder to construct effective representations of relations between objects, and a nearest class mean (NCM) classifier to conduct relation prediction based on relation feature similarities. Extensive experimental results show that the proposed ERBNet outperforms several state-of-the-art methods on the challenging Visual Genome dataset.

Despite the success in large-scale text-to-image generation and text-conditioned image editing, existing methods still struggle to produce consistent generation and editing results. For example, generation approaches usually fail to synthesize multiple images of the same objects/characters but with different views or poses. Meanwhile, existing editing methods either fail to achieve effective complex nonrigid editing while maintaining the overall textures and identity, or require time-consuming fine-tuning to capture the image-specific appearance. In this paper, we develop MasaCtrl, a tuning-free method to achieve consistent image generation and complex non-rigid image editing simultaneously. Specifically, MasaCtrl converts existing self-attention in diffusion models into mutual self-attention, so that it can query correlated local contents and textures from source images for consistency. To further alleviate the query confusion between foreground and background, we propose a mask-guided mutual self-attention strategy, where the mask can be easily extracted from the cross-attention maps. Extensive experiments show that the proposed MasaCtrl can produce impressive results in both consistent image generation and complex non-rigid real image editing.

Video Tagging intends to infer multiple tags spanning relevant content for a given video. Typically, video tags are freely defined and uploaded by a variety of users, so they have two characteristics: abundant in quantity and disordered intra-video. It is difficult for the existing multilabel classification and generation methods to adapt directly to this task. This paper proposes a novel generative model, Order-Prompted Tag Sequence Generation (OP-TSG), according to the above characteristics. It regards video tagging as a tag sequence generation problem guided by sample-dependent order prompts. These prompts are semantically aligned with tags and enable to decouple tag generation order, making the model focus on modeling the tag dependencies. Moreover, the word-based generation strategy enables the model to generate novel tags. To verify the effectiveness and generalization of the proposed method, a Chinese video tagging benchmark CREATE-tagging, and an English image tagging benchmark Pexel-tagging are established. Extensive results show that OP-TSG is significantly superior to other methods, especially the results on rare tags improve by 3.3% and 3% over SOTA methods on CREATE-tagging and Pexel-tagging, and novel tags generated on CREATE-tagging exhibit a tag gain of 7.04%.

Recognizing and segmenting actions from long videos is a challenging problem. Most existing methods focus on designing temporal convolutional models. However, these models are limited in their flexibility and ability to model long-term dependencies. Transformers have recently been used in various tasks. But the lack of inductive bias and the inefficiency of handling long video sequences limit the application of Transformers in action segmentation. In this paper, we present a pure Transformer-based model without temporal convolutions in action segmentation, called Temporal U-Transformer. The U-Transformer architecture not only reduces complexity but also introduces an inductive bias that neighboring frames are more likely to belong to the same class. Besides, we further propose a boundary-aware loss based on the distribution of similarity scores between frames from attention modules to improve the ability to recognize boundaries. Extensive experiments show the effectiveness of our method.

As an important and challenging problem in computer vision, PAnoramic Semantic Segmentation (PASS) gives complete scene perception based on an ultra-wide angle of view. Usually, prevalent PASS methods with 2D panoramic image input focus on solving image distortions but lack consideration of the 3D properties of original 360 degree data. Therefore, their performance will drop a lot when inputting panoramic images with the 3D disturbance. To be more robust to 3D disturbance, we propose our Spherical Geometry-Aware Transformer for PAnoramic Semantic Segmentation (SGAT4PASS), considering 3D spherical geometry knowledge. Specifically, a spherical geometry-aware framework is proposed for PASS. It includes three modules, i.e., spherical geometry-aware image projection, spherical deformable patch embedding, and a panorama-aware loss, which takes input images with 3D disturbance into account, adds a spherical geometry-aware constraint on the existing deformable patch embedding, and indicates the pixel density of original 360 degree data, respectively. Experimental results on Stanford2D3D Panoramic datasets show that SGAT4PASS significantly improves performance and robustness, with approximately a 2% increase in mIoU, and when small 3D disturbances occur in the data, the stability of our performance is improved by an order of magnitude. Our code and supplementary material are available at https://github.com/TencentARC/SGAT4PASS.

Video thumbnail plays an essential role in summarizing video content into a compact and concise image for users to browse efficiently. However, automatically generating attractive and informative video thumbnails remains an open problem due to the difficulty of formulating human aesthetic perception and the scarcity of paired training data. This work proposes a novel Human Perception-Centric Video Thumbnail Generation (HPCVTG) to address these challenges. Specifically, our framework first generates a set of thumbnails using a principle-based system, which conforms to established aesthetic and human perception principles, such as visual balance in the layout and avoiding overlapping elements. Then rather than designing from scratch, we ask human annotators to evaluate some of these thumbnails and select their preferred ones. A Transformer-based Variational Auto-Encoder (VAE) model is firstly pre-trained with Model-Agnostic Meta-Learning (MAML) and then fine-tuned on these human-selected thumbnails. The exploration of combining the MAML pre-training paradigm with human feedback in training can reduce human involvement and make the training process more efficient. Extensive experimental results show that our HPCVTG framework outperforms existing methods in objective and subjective evaluations, highlighting its potential to improve the user experience when browsing videos and inspire future research in human perception-centric content generation tasks. The code and dataset will be released via https://github.com/yangtao2019yt/HPCVTG.

The rapid explosion of video distribution is accompanied by a massive amount of video text, which encompasses rich information about the video content. While previous research has primarily focused on text extraction from videos like text detection, tracking, recognition and end to end spotting, the layout of video text has received limited attention. As different text categories convey distinct meanings, video text layout is critical for video understanding tasks such as video summarization and shooting environment comprehension. To bridge the gap between video OCR and understanding, we explore the study of video text layout in this work. We first optimize the layout annotation of the BOVText, a bilingual, open-world video text dataset, by expanding text categories and defining five clear categories: scene, subtitle, title, logo, and other. Additionally, we rectify the original unreasonable layout annotation based on these definitions. We also propose a Video-level Text Layout model (VTLayout) to address the layout problem, which fuses textual, visual, and spatial-temporal embedding of video text trajectories. To the best of our knowledge, this is the first method to tackle text layout on video level. Our method outperforms image-level layout methods across all text categories and exhibits faster inference speed. This study underscores the significance of video text layout in video understanding and offers an effective solution to this challenge. Our annotation is available at https://github.com/TencentARC/VTLayout.

3D visual grounding, the task of identifying visual objects in 3D scenes based on natural language inputs, plays a critical role in enabling machines to understand and engage with the real-world environment. However, this task is challenging due to the necessity to capture 3D contextual information to distinguish target objects from complex 3D scenes. The absence of annotations for contextual objects and relations further exacerbates the difficulties. In this paper, we propose a novel model, CORE-3DVG, to address these challenges by explicitly learning about contextual objects and relations. Our method accomplishes 3D visual grounding via three sequential modular networks, including a text-guided object detection network, a relation matching network, and a target identification network. During training, we introduce a pseudo-label self-generation strategy and a weakly-supervised method to facilitate the learning of contextual objects and relations, respectively. The proposed techniques allow the networks to focus more effectively on referred objects within 3D scenes by understanding their context better. We validate our model on the challenging Nr3D, Sr3D, and ScanRefer datasets and demonstrate state-of-the-art performance. Our code will be public at https://github.com/yangli18/CORE-3DVG.

Few-shot action recognition has attracted increasing attention in recent years, but it remains challenging due to the intrinsic difficulty in learning transferable knowledge to generalize to novel classes by using a few labeled samples. Although some successful progress has been made, most few-shot action recognition methods commonly focus on the global characteristics of samples while ignoring the local characteristics of samples, which results in the weak generalization ability of the model. In this paper, we propose a task-aware dual-representation network (TADRNet) for few-shot action recognition, which learns how to adapt video representations to novel tasks in a meta-learning manner. It mainly includes a global relational graph subnetwork (GRG) and a fine-grained local representation subnetwork (FLR). Our method simultaneously considers both global and local characteristics of samples for few-shot action recognition. From a global perspective, we propose GRG to explore the relations across support-query sample pairs by using the relational graph neural network. To facilitate the few-shot visual learning, we propose a novel hybrid semantic attention module (HSA) for enhancing the discriminability of support and query features. From a local perspective, we utilize FLR to fully exploit the local characteristics of samples, which can improve the classification results obtained by GRG and thus guarantee high classification accuracy. Extensive experiments on four challenging benchmarks show that the proposed TADRNet significantly outperforms a variety of state-of-the-art few-shot action recognition methods.

As a prerequisite of many text-related tasks such as text erasing and text style transfer, text segmentation arouses more and more attention recently. Current researches mainly focus on only English characters and digits, while few work studies Chinese characters due to the lack of pub-lic large-scale and high-quality Chinese datasets, which limits the practical application scenarios of text segmentation. Different from English which has a limited alphabet of letters, Chinese has much more basic characters with com-plex structures, making the problem more difficult to deal with. To better analyze this problem, we propose the Bi-lingual Text Segmentation (BTS) dataset, a benchmark that covers various common Chinese scenes including 14,250 diverse and fine-annotated text images. BTS mainly focuses on Chinese characters, and also contains English words and digits. We also introduce Prior Guided Text Segmen-tation Network (PGTSNet), the first baseline to handle bi-lingual and complex-structured text segmentation. A plug-in text region highlighting module and a text perceptual dis-criminator are proposed in PGTSNet to supervise the model with text prior, and guide for more stable and finer text seg-mentation. A variation loss is also employed for suppressing background noise under complex scene. Extensive ex-periments are conducted not only to demonstrate the neces-sity and superiority of the proposed dataset BTS, but also to show the effectiveness of the proposed PGTSNet compared with a variety of state-of-the-art text segmentation methods.

Action classification has made great progress, but segmenting and recognizing actions from long videos remains a challenging problem. Recently, Transformer-based models with strong sequence modeling ability have succeeded in many se-quence modeling tasks. However, the lack of inductive bias and the difficulty of handling long video sequences limit the application of the Transformer in the action segmentation task. In order to explore the potential of the Transformer in this task, we replace some specific linear layers in the vanilla Transformer with dilated temporal convolution, and a sparse attention mechanism is utilized to reduce the time and space complexities to process long video sequences. Besides, directly using frame-wise classification loss to train the model will cause that frames at boundaries of actions are treated equally with those in the middle of actions, and the learned features are not sensitive to boundaries. We propose a new local log-context attention module to predict whether each frame is at the beginning, middle, or end of an action. Since boundary frames are similar to their neighboring frames of different classes, our similarity-based boundary prediction helps learn more discriminative features. Extensive experiments on three datasets show the effectiveness of our method.

In this paper, we convert traditional video captioning task into a new paradigm, i.e., Open-book Video Captioning, which generates natural language under the prompts of video-content-relevant sentences, not limited to the video itself. To address the open-book video captioning problem, we propose a novel Retrieve-Copy-Generate network, where a pluggable video-to-text retriever is constructed to retrieve sentences as hints from the training corpus effectively, and a copy-mechanism generator is introduced to extract expressions from multi-retrieved sentences dynamically. The two modules can be trained end-to-end or separately, which is flexible and extensible. Our framework co-ordinates the conventional retrieval-based methods with orthodox encoder-decoder methods, which can not only draw on the diverse expressions in the retrieved sentences but also generate natural and accurate content of the video. Extensive experiments on several benchmark datasets show that our proposed approach surpasses the state-of-the-art performance, indicating the effectiveness and promising of the proposed paradigm in the task of video captioning.

Tag inference is an important task in the business of video platforms with wide applications such as recommendation, interpretation, and more. Existing works are mainly based on extracting video information from multiple modalities such as frames or music, and then infer tags through classification or object detection. This, however, does not apply to inferring generic tags or taxonomy that are less relevant to video contents, such as video originality or its broader category, which are important in practice. In this paper, we claim that these generic tags can be modeled through the semantic relations between videos and tags, and can be utilized simultaneously with the multi-modal features to achieve better video tagging. We propose TransFusion, an end-to-end supervised learning framework that fuses multi-modal embeddings (e.g., vision, audio, texts, etc.) with the knowledge embedding to derive the video representation. To infer the diverse tags following heterogeneous relations, TransFusion adopts a dual attentive approach to learn both the modality importance in fusion and relation importance in inference. Besides, it is general enough and can be used with the existing translation-based knowledge embedding approaches. Extensive experiments show that TransFusion outperforms the baseline methods with lowered mean rank and at least 9.59% improvement in [email protected] on the real-world video knowledge graph.

Few-shot action recognition has drawn growing attention as it can recognize novel action classes by using only a few labeled samples. In this paper, we propose a novel semantic-guided relation propagation network (SRPN), which leverages semantic information together with visual information for few-shot action recognition. Different from most previous works that neglect semantic information in the labeled data, our SRPN directly utilizes the semantic label as an additional supervisory signal to improve the generalization ability of the network. Besides, we treat the relation of each visual-semantic pair as a relational node, and we use a graph convolutional network to model and propagate such sample relations across visual-semantic pairs, including both intra-class commonality and inter-class uniqueness, to guide the relation propagation in the graph. However, since videos contain crucial sequences and ordering information, we propose a novel spatial-temporal difference module, which can facilitate the network to enhance the visual feature learning ability at both feature level and granular level for videos. Extensive experiments conducted on several challenging benchmarks demonstrate that our SRPN outperforms several state-of-the-art methods with a significant margin.

Recent blind super-resolution (SR) methods typically consist of two branches, one for degradation prediction and the other for conditional restoration. However, our experiments show that a one-branch network can achieve comparable performance to the two-branch scheme. Then we wonder: how can one-branch networks automatically learn to distinguish degradations? To find the answer, we propose a new diagnostic tool -- Filter Attribution method based on Integral Gradient (FAIG). Unlike previous integral gradient methods, our FAIG aims at finding the most discriminative filters instead of input pixels/features for degradation removal in blind SR networks. With the discovered filters, we further develop a simple yet effective method to predict the degradation of an input image. Based on FAIG, we show that, in one-branch blind SR networks, 1) we could find a very small number of (1%) discriminative filters for each specific degradation; 2) The weights, locations and connections of the discovered filters are all important to determine the specific network function. 3) The task of degradation prediction can be implicitly realized by these discriminative filters without explicit supervised learning. Our findings can not only help us better understand network behaviors inside one-branch blind SR networks, but also provide guidance on designing more efficient architectures and diagnosing networks for blind SR.

Understanding and interpreting the decisions made by deep learning models is valuable in many domains. In computer vision, computing heatmaps from a deep network is a popular approach for visualizing and understanding deep networks. However, heatmaps that do not correlate with the network may mislead human, hence the performance of heatmaps in providing a faithful explanation to the underlying deep network is crucial. In this paper, we propose I-GOS, which optimizes for a heatmap so that the classification scores on the masked image would maximally decrease. The main novelty of the approach is to compute descent directions based on the integrated gradients instead of the normal gradient, which avoids local optima and speeds up convergence. Compared with previous approaches, our method can flexibly compute heatmaps at any resolution for different user needs. Extensive experiments on several benchmark datasets show that the heatmaps produced by our approach are more correlated with the decision of the underlying deep network, in comparison with other state-of-the-art approaches.

Unlike images which are represented in regular dense grids, 3D point clouds are irregular and unordered, hence applying convolution on them can be difficult. In this paper, we extend the dynamic filter to a new convolution operation, named PointConv. PointConv can be applied on point clouds to build deep convolutional networks. We treat convolution kernels as nonlinear functions of the local coordinates of 3D points comprised of weight and density functions. With respect to a given point, the weight functions are learned with multi-layer perceptron networks and the density functions through kernel density estimation. A novel reformulation is proposed for efficiently computing the weight functions, which allowed us to dramatically scale up the network and significantly improve its performance. The learned convolution kernel can be used to compute translation-invariant and permutation-invariant convolution on any point set in the 3D space. Besides, PointConv can also be used as deconvolution operators to propagate features from a subsampled point cloud back to its original resolution. Experiments on ModelNet40, ShapeNet, and ScanNet show that deep convolutional neural networks built on PointConv are able to achieve state-of-the-art on challenging semantic segmentation benchmarks on 3D point clouds. Besides, our experiments converting CIFAR-10 into a point cloud showed that networks built on PointConv can match the performance of convolutional networks in 2D images of a similar structure.

Medical concept normalization is a critical problem in biomedical research and clinical applications. In this paper, we focus on normalizing diagnostic and procedure names in Chinese discharge summaries to standard entities, which is formulated as a semantic matching problem. However, non-standard Chinese expressions, short-text normalization and heterogeneity of tasks pose critical challenges in our problem. This paper presents a general framework which introduces a tensor generator and a novel multi-view convolutional neural network (CNN) with multi-task shared structure to tackle the two tasks simultaneously. We propose that the key to address non-standard expressions and short-text problem is to incorporate a matching tensor with multiple granularities. Then multi-view CNN is adopted to extract semantic matching patterns and learn to synthesize them from different views. Finally, multi-task shared structure allows the model to exploit medical correlations between disease and procedure names to better perform disambiguation tasks. Comprehensive experimental analysis indicates our model outperforms existing baselines which demonstrates the effectiveness of our model.

The interpolation, prediction, and feature analysis of fine-gained air quality are three important topics in the area of urban air computing. The solutions to these topics can provide extremely useful information to support air pollution control, and consequently generate great societal and technical impacts. Most of the existing work solves the three problems separately by different models. In this paper, we propose a general and effective approach to solve the three problems in one model called the Deep Air Learning (DAL). The main idea of DAL lies in embedding feature selection and semi-supervised learning in different layers of the deep learning network. The proposed approach utilizes the information pertaining to the unlabeled spatio-temporal data to improve the performance of the interpolation and the prediction, and performs feature selection and association analysis to reveal the main relevant features to the variation of the air quality. We evaluate our approach with extensive experiments based on real data sources obtained in Beijing, China. Experiments show that DAL is superior to the peer models from the recent literature when solving the topics of interpolation, prediction, and feature analysis of fine-gained air quality.

In this paper, we study the multi-task learning problem with a new perspective of considering the link structure of data and task relationship modeling simultaneously. In particular, we first introduce the Matrix Gaussian (MG) distribution and Matrix Generalized Inverse Gaussian (MGIG) distribution, then define a Matrix Gaussian Matrix Generalized Inverse Gaussian (MG-MGIG) prior. Based on this prior, we propose a novel multi-task learning algorithm, the Bayesian Multi-task Relationship Learning (BMTRL) algorithm. To incorporate the link structure into the framework of BMTRL, we propose link constraints between samples. Through combining the BMTRL algorithm with the link constraints, we propose the Bayesian Multi-task Relationship Learning with Link Constraints (BMTRL-LC) algorithm. Further, we apply the manifold theory to provide an extension of BMTRL-LC to data with no link structure. Specifically, BMTRL-LC is effective for multi-task learning with only limited training samples, which is not addressed in the existing literature. To make the computation tractable, we simultaneously use a convex optimization method and sampling techniques. In particular, we adopt two stochastic EM algorithms for BMTRL and BMTRL-LC, respectively. The experimental results on three real datasets demonstrate the promise of the proposed algorithms.

In this paper, we study the multi-task learning problem with a new perspective of considering the link structure of data and task relationship modeling simultaneously. In particular, we first introduce the Matrix Generalized Inverse Gaussian (MGIG) distribution and define a Matrix Gaussian Matrix Generalized Inverse Gaussian (MG-MGIG) prior. Based on this prior, we propose a novel multi-task learning algorithm, the Bayesian Multi-task Relationship Learning (BMTRL) algorithm. To incorporate the link structure into the framework of BMTRL, we propose link constraints between samples. Through combining the BMTRL algorithm with the link constraints, we propose the Bayesian Multi-task Relationship Learning with Link Constraints (BMTRL-LC) algorithm. To make the computation tractable, we simultaneously use a convex optimization method and sampling techniques. In particular, we adopt two stochastic EM algorithms for BMTRL and BMTRL-LC, respectively. The experimental results on Cora dataset demonstrate the promise of the proposed algorithms.

With the rapid development of social networks, tagging has become an important means responsible for such rapid development. A robust tagging method must have the capability to meet the two challenging requirements: limited labeled training samples and noisy labeled training samples. In this paper, we investigate this challenging problem of learning with limited and noisy tagging and propose a discriminative model, called SpSVM-MC, that exploits both labeled and unlabeled data through a semi-parametric regularization and takes advantage of the multi-label constraints into the optimization. While SpSVM-MC is a general method for learning with limited and noisy tagging, in the evaluations we focus on the specific application of noisy image tagging with limited labeled training samples on a benchmark dataset. Theoretical analysis and extensive evaluations in comparison with state-of-the-art literature demonstrate that SpSVM-MC outstands with a superior performance.

In this paper we study the problem of mining noisy tagging. Most of the existing discriminative classification methods to this problem only consider one tag at a time as the classification target, and completely ignore the rest of the given tags at the same time. In this paper we argue that all the given multiple tags can be utilized simultaneously as an additional feature and the information contained in the multi-label space can be taken advantage of to improve the performance of the classification. We first propose a novel distance measure to compute the distance between instances in the multi-label space. Then we propose several novel methods to incorporate the information of the multi-label space into the discriminative classification methods in one view learning or in two views learning to solve a general multi-label classification problem and to mitigate the influence of the noise in the classification. We apply the proposed solutions to the problem with a more specific context - noisy image annotation, and evaluate the proposed methods on a standard dataset from the related literature. Experiments show that they are superior to the peer methods in the existing literature on solving the problem of mining noisy tagging.

In many real-world applications, tagging is imperfect: incomplete, inconsistent, and error-prone. Solutions to this problem will generate societal and technical impacts. In this paper, we investigate this arguably new problem: learning from imperfect tagging. We propose a general and effective learning scheme called the Multi-view Imperfect Tagging Learning (MITL) to this problem. The main idea of MITL lies in extracting the information of the imperfectly tagged training dataset from multiple views to differentiate the data points in the role of classification. Further, a novel discriminative classification method is proposed under the framework of MITL, which explicitly makes use of the given multiple labels simultaneously as an additional feature to deliver a more effective classification performance than the existing literature where one label is considered at a time as the classification target while the rest of the given labels are completely ignored at the same time. The proposed methods can not only complete the incomplete tagging but also denoise the noisy tagging through an inductive learning. We apply the general solution to the problem with a more specific context - imperfect image annotation, and evaluate the proposed methods on a standard dataset from the related literature. Experiments show that they are superior to the peer methods on solving the problem of learning from imperfect tagging in cross-media.

In this paper, we study the problem of mining partially annotated images. We first define what the problem of mining partially annotated images is, and argue that in many real-world applications annotated images are typically partially annotated and thus that the problem of mining partially annotated images exists in many situations. We then propose an effective solution to this problem based on a statistical model we have developed called the Semi-Supervised Correspondence Hierarchical Dirichlet Process (SSCHDP). The main idea of this model lies in exploiting the information pertaining to partially annotated images or even unannotated images to achieve semi-supervised learning under the HDP structure. We apply this model to completing the annotations appropriately for partially annotated images in the training data and then to predicting the annotations appropriately and completely for all the unannotated images either in the training data or in any unseen data beyond the training process. Experiments show that SSC-HDP is superior to the peer models from the recent literature when they are applied to solving the problem of mining partially annotated images.