Jingjia Huang

Ruyang Liu, Jingjia Huang, Ge Li et al.

Image-text pretrained models, e.g., CLIP, have shown impressive general multi-modal knowledge learned from large-scale image-text data pairs, thus attracting increasing attention for their potential to improve visual representation learning in the video domain. In this paper, based on the CLIP model, we revisit temporal modeling in the context of image-to-video knowledge transferring, which is the key point for extending image-text pretrained models to the video domain. We find that current temporal modeling mechanisms are tailored to either high-level semantic-dominant tasks (e.g., retrieval) or low-level visual pattern-dominant tasks (e.g., recognition), and fail to work on the two cases simultaneously. The key difficulty lies in modeling temporal dependency while taking advantage of both high-level and low-level knowledge in CLIP model. To tackle this problem, we present Spatial-Temporal Auxiliary Network (STAN) -- a simple and effective temporal modeling mechanism extending CLIP model to diverse video tasks. Specifically, to realize both low-level and high-level knowledge transferring, STAN adopts a branch structure with decomposed spatial-temporal modules that enable multi-level CLIP features to be spatial-temporally contextualized. We evaluate our method on two representative video tasks: Video-Text Retrieval and Video Recognition. Extensive experiments demonstrate the superiority of our model over the state-of-the-art methods on various datasets, including MSR-VTT, DiDeMo, LSMDC, MSVD, Kinetics-400, and Something-Something-V2. Codes will be available at https://github.com/farewellthree/STAN

Jingjia Huang, Yinan Li, Jiashi Feng et al.

Building a universal Video-Language model for solving various video understanding tasks (\emph{e.g.}, text-video retrieval, video question answering) is an open challenge to the machine learning field. Towards this goal, most recent works build the model by stacking uni-modal and cross-modal feature encoders and train it with pair-wise contrastive pre-text tasks. Though offering attractive generality, the resulted models have to compromise between efficiency and performance. They mostly adopt different architectures to deal with different downstream tasks. We find this is because the pair-wise training cannot well \emph{align} and \emph{fuse} features from different modalities. We then introduce \textbf{Clover}\textemdash a Correlated Video-Language pre-training method\textemdash towards a universal Video-Language model for solving multiple video understanding tasks with neither performance nor efficiency compromise. It improves cross-modal feature alignment and fusion via a novel tri-modal alignment pre-training task. Additionally, we propose to enhance the tri-modal alignment via incorporating learning from semantic masked samples and a new pair-wise ranking loss. Clover establishes new state-of-the-arts on multiple downstream tasks, including three retrieval tasks for both zero-shot and fine-tuning settings, and eight video question answering tasks. Codes and pre-trained models will be released at \url{https://github.com/LeeYN-43/Clover}.

Jingjia Huang, Yuanqi Chen, Jiashi Feng et al. · pku

Semi-supervised learning based methods are current SOTA solutions to the noisy-label learning problem, which rely on learning an unsupervised label cleaner first to divide the training samples into a labeled set for clean data and an unlabeled set for noise data. Typically, the cleaner is obtained via fitting a mixture model to the distribution of per-sample training losses. However, the modeling procedure is \emph{class agnostic} and assumes the loss distributions of clean and noise samples are the same across different classes. Unfortunately, in practice, such an assumption does not always hold due to the varying learning difficulty of different classes, thus leading to sub-optimal label noise partition criteria. In this work, we reveal this long-ignored problem and propose a simple yet effective solution, named \textbf{C}lass \textbf{P}rototype-based label noise \textbf{C}leaner (\textbf{CPC}). Unlike previous works treating all the classes equally, CPC fully considers loss distribution heterogeneity and applies class-aware modulation to partition the clean and noise data. CPC takes advantage of loss distribution modeling and intra-class consistency regularization in feature space simultaneously and thus can better distinguish clean and noise labels. We theoretically justify the effectiveness of our method by explaining it from the Expectation-Maximization (EM) framework. Extensive experiments are conducted on the noisy-label benchmarks CIFAR-10, CIFAR-100, Clothing1M and WebVision. The results show that CPC consistently brings about performance improvement across all benchmarks. Codes and pre-trained models will be released at \url{https://github.com/hjjpku/CPC.git}.

Ruyang Liu, Jingjia Huang, Wei Gao et al.

Large-scale image-language pretrained models, e.g., CLIP, have demonstrated remarkable proficiency in acquiring general multi-modal knowledge through web-scale image-text data. Despite the impressive performance of image-language models on various image tasks, how to effectively expand them on general video understanding remains an area of ongoing exploration. In this paper, we investigate the image-to-video transferring from the perspective of the model and the data, unveiling two key obstacles impeding the adaptation of image-language models: non-generalizable temporal modeling and partially misaligned video-text data. To address these challenges, we propose Spatial-Temporal Auxiliary Network with Mutual-guided alignment module (Mug-STAN), a simple yet effective framework extending image-text model to diverse video tasks and video-text data.Specifically, STAN adopts a branch structure with decomposed spatial-temporal modules to enable generalizable temporal modeling, while Mug suppresses misalignment by introducing token-wise feature aggregation of either modality from the other. Extensive experimental results verify Mug-STAN significantly improves adaptation of language-image pretrained models such as CLIP and CoCa at both video-text post-pretraining and finetuning stages. With our solution, state-of-the-art zero-shot and finetuning results on various downstream datasets, including MSR-VTT, DiDeMo, LSMDC, Kinetics-400, Something-Something-2, HMDB-51, UCF- 101, and AVA, are achieved. Moreover, by integrating pretrained Mug-STAN with the emerging multimodal dialogue model, we can realize zero-shot video chatting. Codes are available at https://github.com/farewellthree/STAN

Fan Ma, Xiaojie Jin, Heng Wang et al.

Video-Language Pre-training models have recently significantly improved various multi-modal downstream tasks. Previous dominant works mainly adopt contrastive learning to achieve global feature alignment across modalities. However, the local associations between videos and texts are not modeled, restricting the pre-training models' generality, especially for tasks requiring the temporal video boundary for certain query texts. This work introduces a novel text-video localization pre-text task to enable fine-grained temporal and semantic alignment such that the trained model can accurately perceive temporal boundaries in videos given the text description. Specifically, text-video localization consists of moment retrieval, which predicts start and end boundaries in videos given the text description, and text localization which matches the subset of texts with the video features. To produce temporal boundaries, frame features in several videos are manually merged into a long video sequence that interacts with a text sequence. With the localization task, our method connects the fine-grained frame representations with the word representations and implicitly distinguishes representations of different instances in the single modality. Notably, comprehensive experimental results show that our method significantly improves the state-of-the-art performance on various benchmarks, covering text-to-video retrieval, video question answering, video captioning, temporal action localization and temporal moment retrieval. The code will be released soon.

Yabo Zhang, Zihao Wang, Jun Hao Liew et al.

In this work, we investigate performing semantic segmentation solely through the training on image-sentence pairs. Due to the lack of dense annotations, existing text-supervised methods can only learn to group an image into semantic regions via pixel-insensitive feedback. As a result, their grouped results are coarse and often contain small spurious regions, limiting the upper-bound performance of segmentation. On the other hand, we observe that grouped results from self-supervised models are more semantically consistent and break the bottleneck of existing methods. Motivated by this, we introduce associate self-supervised spatially-consistent grouping with text-supervised semantic segmentation. Considering the part-like grouped results, we further adapt a text-supervised model from image-level to region-level recognition with two core designs. First, we encourage fine-grained alignment with a one-way noun-to-region contrastive loss, which reduces the mismatched noun-region pairs. Second, we adopt a contextually aware masking strategy to enable simultaneous recognition of all grouped regions. Coupled with spatially-consistent grouping and region-adapted recognition, our method achieves 59.2% mIoU and 32.4% mIoU on Pascal VOC and Pascal Context benchmarks, significantly surpassing the state-of-the-art methods.

Rui Yang, Ziyu Zhu, Yanwei Li et al.

Capturing spatial relationships from visual inputs is a cornerstone of human-like general intelligence. Several previous studies have tried to enhance the spatial awareness of Vision-Language Models (VLMs) by adding extra expert encoders, which brings extra overhead and usually harms general capabilities. To enhance the spatial ability in general architectures, we introduce Visual Spatial Tuning (VST), a comprehensive framework to cultivate VLMs with human-like visuospatial abilities, from spatial perception to reasoning. We first attempt to enhance spatial perception in VLMs by constructing a large-scale dataset termed VST-P, which comprises 4.1 million samples spanning 19 skills across single views, multiple images, and videos. Then, we present VST-R, a curated dataset with 135K samples that instruct models to reason in space. In particular, we adopt a progressive training pipeline: supervised fine-tuning to build foundational spatial knowledge, followed by reinforcement learning to further improve spatial reasoning abilities. Without the side-effect to general capabilities, the proposed VST consistently achieves state-of-the-art results on several spatial benchmarks, including $34.8\%$ on MMSI-Bench and $61.2\%$ on VSIBench. It turns out that the Vision-Language-Action models can be significantly enhanced with the proposed spatial tuning paradigm, paving the way for more physically grounded AI.

Jingjia Huang, Baixiang Yang

Human Object Interaction (HOI) detection is a challenging task that requires to distinguish the interaction between a human-object pair. Attention based relation parsing is a popular and effective strategy utilized in HOI. However, current methods execute relation parsing in a "bottom-up" manner. We argue that the independent use of the bottom-up parsing strategy in HOI is counter-intuitive and could lead to the diffusion of attention. Therefore, we introduce a novel knowledge-guided top-down attention into HOI, and propose to model the relation parsing as a "look and search" process: execute scene-context modeling (i.e. look), and then, given the knowledge of the target pair, search visual clues for the discrimination of the interaction between the pair. We implement the process via unifying the bottom-up and top-down attention in a single encoder-decoder based model. The experimental results show that our model achieves competitive performance on the V-COCO and HICO-DET datasets.

Dong Guo, Faming Wu, Feida Zhu et al. · pku

We present Seed1.5-VL, a vision-language foundation model designed to advance general-purpose multimodal understanding and reasoning. Seed1.5-VL is composed with a 532M-parameter vision encoder and a Mixture-of-Experts (MoE) LLM of 20B active parameters. Despite its relatively compact architecture, it delivers strong performance across a wide spectrum of public VLM benchmarks and internal evaluation suites, achieving the state-of-the-art performance on 38 out of 60 public benchmarks. Moreover, in agent-centric tasks such as GUI control and gameplay, Seed1.5-VL outperforms leading multimodal systems, including OpenAI CUA and Claude 3.7. Beyond visual and video understanding, it also demonstrates strong reasoning abilities, making it particularly effective for multimodal reasoning challenges such as visual puzzles. We believe these capabilities will empower broader applications across diverse tasks. In this report, we mainly provide a comprehensive review of our experiences in building Seed1.5-VL across model design, data construction, and training at various stages, hoping that this report can inspire further research. Seed1.5-VL is now accessible at https://www.volcengine.com/ (Volcano Engine Model ID: doubao-1-5-thinking-vision-pro-250428)

Zhangheng Li, Jia-Xing Zhong, Jingjia Huang et al.

In recent years, memory-augmented neural networks(MANNs) have shown promising power to enhance the memory ability of neural networks for sequential processing tasks. However, previous MANNs suffer from complex memory addressing mechanism, making them relatively hard to train and causing computational overheads. Moreover, many of them reuse the classical RNN structure such as LSTM for memory processing, causing inefficient exploitations of memory information. In this paper, we introduce a novel MANN, the Auto-addressing and Recurrent Memory Integrating Network (ARMIN) to address these issues. The ARMIN only utilizes hidden state ht for automatic memory addressing, and uses a novel RNN cell for refined integration of memory information. Empirical results on a variety of experiments demonstrate that the ARMIN is more light-weight and efficient compared to existing memory networks. Moreover, we demonstrate that the ARMIN can achieve much lower computational overhead than vanilla LSTM while keeping similar performances. Codes are available on github.com/zoharli/armin.

Haoming Wang, Haoyang Zou, Huatong Song et al. · pku

The development of autonomous agents for graphical user interfaces (GUIs) presents major challenges in artificial intelligence. While recent advances in native agent models have shown promise by unifying perception, reasoning, action, and memory through end-to-end learning, open problems remain in data scalability, multi-turn reinforcement learning (RL), the limitations of GUI-only operation, and environment stability. In this technical report, we present UI-TARS-2, a native GUI-centered agent model that addresses these challenges through a systematic training methodology: a data flywheel for scalable data generation, a stabilized multi-turn RL framework, a hybrid GUI environment that integrates file systems and terminals, and a unified sandbox platform for large-scale rollouts. Empirical evaluation demonstrates that UI-TARS-2 achieves significant improvements over its predecessor UI-TARS-1.5. On GUI benchmarks, it reaches 88.2 on Online-Mind2Web, 47.5 on OSWorld, 50.6 on WindowsAgentArena, and 73.3 on AndroidWorld, outperforming strong baselines such as Claude and OpenAI agents. In game environments, it attains a mean normalized score of 59.8 across a 15-game suite-roughly 60% of human-level performance-and remains competitive with frontier proprietary models (e.g., OpenAI o3) on LMGame-Bench. Additionally, the model can generalize to long-horizon information-seeking tasks and software engineering benchmarks, highlighting its robustness across diverse agent tasks. Detailed analyses of training dynamics further provide insights into achieving stability and efficiency in large-scale agent RL. These results underscore UI-TARS-2's potential to advance the state of GUI agents and exhibit strong generalization to real-world interactive scenarios.

Jingjia Huang, Nannan Li, Tao Zhang et al.

Existing action detection algorithms usually generate action proposals through an extensive search over the video at multiple temporal scales, which brings about huge computational overhead and deviates from the human perception procedure. We argue that the process of detecting actions should be naturally one of observation and refinement: observe the current window and refine the span of attended window to cover true action regions. In this paper, we propose an active action proposal model that learns to find actions through continuously adjusting the temporal bounds in a self-adaptive way. The whole process can be deemed as an agent, which is firstly placed at a position in the video at random, adopts a sequence of transformations on the current attended region to discover actions according to a learned policy. We utilize reinforcement learning, especially the Deep Q-learning algorithm to learn the agent's decision policy. In addition, we use temporal pooling operation to extract more effective feature representation for the long temporal window, and design a regression network to adjust the position offsets between predicted results and the ground truth. Experiment results on THUMOS 2014 validate the effectiveness of the proposed approach, which can achieve competitive performance with current action detection algorithms via much fewer proposals.