Existing multimodal generative models fall short as qualified design copilots, as they often struggle to generate imaginative outputs once instructions are less detailed or lack the ability to maintain consistency with the provided references. In this work, we introduce WeGen, a model that unifies multimodal generation and understanding, and promotes their interplay in iterative generation. It can generate diverse results with high creativity for less detailed instructions. And it can progressively refine prior generation results or integrating specific contents from references following the instructions in its chat with users. During this process, it is capable of preserving consistency in the parts that the user is already satisfied with. To this end, we curate a large-scale dataset, extracted from Internet videos, containing rich object dynamics and auto-labeled dynamics descriptions by advanced foundation models to date. These two information are interleaved into a single sequence to enable WeGen to learn consistency-aware generation where the specified dynamics are generated while the consistency of unspecified content is preserved aligned with instructions. Besides, we introduce a prompt self-rewriting mechanism to enhance generation diversity. Extensive experiments demonstrate the effectiveness of unifying multimodal understanding and generation in WeGen and show it achieves state-of-the-art performance across various visual generation benchmarks. These also demonstrate the potential of WeGen as a user-friendly design copilot as desired. The code and models will be available at https://github.com/hzphzp/WeGen.

Recent advancements in multimodal vision models have highlighted limitations in late-stage feature fusion and suboptimal query selection for hybrid prompts open-world segmentation, alongside constraints from caption-derived vocabularies. To address these challenges, we propose Prompt-DINO, a text-guided visual Prompt DINO framework featuring three key innovations. First, we introduce an early fusion mechanism that unifies text/visual prompts and backbone features at the initial encoding stage, enabling deeper cross-modal interactions to resolve semantic ambiguities. Second, we design order-aligned query selection for DETR-based architectures, explicitly optimizing the structural alignment between text and visual queries during decoding to enhance semantic-spatial consistency. Third, we develop a generative data engine powered by the Recognize Anything via Prompting (RAP) model, which synthesizes 0.5B diverse training instances through a dual-path cross-verification pipeline, reducing label noise by 80.5% compared to conventional approaches. Extensive experiments demonstrate that Prompt-DINO achieves state-of-the-art performance on open-world detection benchmarks while significantly expanding semantic coverage beyond fixed-vocabulary constraints. Our work establishes a new paradigm for scalable multimodal detection and data generation in open-world scenarios. Data&Code are available at https://github.com/WeChatCV/WeVisionOne.

Long-tail distribution includes two kinds of imbalance: the class-wise imbalance and the attribute-wise one. Sufficient studies have been conducted on the class-wise imbalance. However, the distribution with both the class-wise and the attribute-wise imbalance is more difficult since the attribute is unknown. To solve this problem, we introduce a novel Generalized Long-tail Exact Penalty Method (GL-EPM). GLEPM redefines the long-tail classification as a constrained optimization problem where the model’s prediction on all samples, both the head samples and the tail samples, are constrained to ally with their labels. We then tackles the constrained problem using the exact penalty method, transforming the problem into a series of unconstrained penalty problems. Each penalty problem in the series is generated by the solution of the previous one and the solution series can be theoretically proved to converge to the solution of the constrained optimization problem. We further solve the penalty problems with a rapid-update solution, where the model is trained with dynamically updated sampling rates and loss weights. To validate the efficacy of our proposed method, we conduct a fair comparison with existing baselines across all generalized long-tail benchmarks, demonstrating state-of-the-art performance.

Existing methods of adversarial attacks successfully generate adversarial examples to confuse Deep Neural Networks (DNNs) of image classification and object detection, resulting in wrong predictions. However, these methods are difficult to attack models of video object tracking, because the tracking algorithms could handle sequential information across video frames and the categories of targets tracked are normally unknown in advance. In this paper, we propose a Unified and Effective Network, named UEN, to attack visual object tracking models. There are several appealing characteristics of UEN: (1) UEN could produce various invisible adversarial perturbations according to different attack settings by using only one simple end-to-end network with three ingenious loss function; (2) UEN could generate general visible adversarial patch patterns to attack the advanced trackers in the real-world; (3) Extensive experiments show that UEN is able to attack many state-of-the-art trackers effectively (e.g. SiamRPN-based networks and DiMP) on popular tracking datasets including OTB100, UAV123, and GOT10K, making online real-time attacks possible. The attack results outperform the introduced baseline in terms of attacking ability and attacking efficiency.

Employing attention mechanisms to model both global and local features as a final pedestrian representation has become a trend for person re-identification (Re-ID) algorithms. A potential limitation of these methods is that they focus on the most salient features, but the re-identification of a person may rely on diverse clues masked by the most salient features in different situations, e.g., body, clothes or even shoes. To handle this limitation, we propose a novel Salience-guided Cascaded Suppression Network (SCSN) which enables the model to mine diverse salient features and integrate these features into the final representation by a cascaded manner. Our work makes the following contributions: (i) We observe that the previously learned salient features may hinder the network from learning other important information. To tackle this limitation, we introduce a cascaded suppression strategy, which enables the network to mine diverse potential useful features that be masked by the other salient features stage-by-stage and each stage integrates different feature embedding for the last discriminative pedestrian representation. (ii) We propose a Salient Feature Extraction (SFE) unit, which can suppress the salient features learned in the previous cascaded stage and then adaptively extracts other potential salient feature to obtain different clues of pedestrians. (iii) We develop an efficient feature aggregation strategy that fully increases the network’s capacity for all potential salience features. Finally, experimental results demonstrate that our proposed method outperforms the state-of-the-art methods on four large-scale datasets. Especially, our approach exceeds the current best method by over 7% on the CUHK03 dataset.

Typical methods for supervised sequence modeling are built upon the recurrent neural networks to capture temporal dependencies. One potential limitation of these methods is that they only model explicitly information interactions between adjacent time steps in a sequence, hence the high-order interactions between nonadjacent time steps are not fully exploited. It greatly limits the capability of modeling the long-range temporal dependencies since one-order interactions cannot be maintained for a long term due to information dilution and gradient vanishing. To tackle this limitation, we propose the Non-local Recurrent Neural Memory (NRNM) for supervised sequence modeling, which performs non-local operations to learn full-order interactions within a sliding temporal block and models the global interactions between blocks in a gated recurrent manner. Consequently, our model is able to capture the long-range dependencies. Besides, the latent high-level features contained in high-order interactions can be distilled by our model. We demonstrate the merits of our NRNM approach on two different tasks: action recognition and sentiment analysis.