Recent advancement in multimodal LLMs (MLLMs) has demonstrated their remarkable capability to generate descriptive captions for input videos. However, these models suffer from factual inaccuracies in the generated descriptions, causing severe hallucination issues. While prior works have explored alleviating hallucinations for static images, jointly mitigating visual object and temporal action hallucinations for dynamic videos remains a challenging and unsolved task. To tackle this challenge, we propose a Self-Augmented Contrastive Alignment (SANTA) framework for enabling object and action faithfulness by exempting the spurious correlations and enforcing the emphasis on visual facts. SANTA employs a hallucinative self-augmentation scheme to identify the potential hallucinations that lie in the MLLM and transform the original captions to the contrasted negatives. Furthermore, we develop a tracklet-phrase contrastive alignment to match the regional objects and relation-guided actions with their corresponding visual and temporal phrases. Extensive experiments demonstrate that SANTA outperforms existing methods in alleviating object and action hallucinations, yielding superior performance on the hallucination examination benchmarks.

Dense video captioning aims to interpret and describe all temporally localized events throughout an input video. Recent state-of-the-art methods leverage large language models (LLMs) to provide detailed moment descriptions for video data. However, existing VideoLLMs remain challenging in identifying precise event boundaries in untrimmed videos, causing the generated captions to be not properly grounded. In this paper, we propose TA-Prompting, which enhances VideoLLMs via Temporal Anchors that learn to precisely localize events and prompt the VideoLLMs to perform temporal-aware video event understanding. During inference, in order to properly determine the output caption sequence from an arbitrary number of events presented within a video, we introduce an event coherent sampling strategy to select event captions with sufficient coherence across temporal events and cross-modal similarity with the given video. Through extensive experiments on benchmark datasets, we show that our TA-Prompting is favorable against state-of-the-art VideoLLMs, yielding superior performance on dense video captioning and temporal understanding tasks including moment retrieval and temporalQA.

Video anomaly understanding (VAU) aims to provide detailed interpretation and semantic comprehension of anomalous events within videos, addressing limitations of traditional methods that focus solely on detecting and localizing anomalies. However, existing approaches often neglect the deeper causal relationships and interactions between objects, which are critical for understanding anomalous behaviors. In this paper, we propose VADER, an LLM-driven framework for Video Anomaly unDErstanding, which integrates keyframe object Relation features with visual cues to enhance anomaly comprehension from video. Specifically, VADER first applies an Anomaly Scorer to assign per-frame anomaly scores, followed by a Context-AwarE Sampling (CAES) strategy to capture the causal context of each anomalous event. A Relation Feature Extractor and a COntrastive Relation Encoder (CORE) jointly model dynamic object interactions, producing compact relational representations for downstream reasoning. These visual and relational cues are integrated with LLMs to generate detailed, causally grounded descriptions and support robust anomaly-related question answering. Experiments on multiple real-world VAU benchmarks demonstrate that VADER achieves strong results across anomaly description, explanation, and causal reasoning tasks, advancing the frontier of explainable video anomaly analysis. Project page is available at https://vader-vau.github.io/.

Customized text-to-video generation aims to produce high-quality videos that incorporate user-specified subject identities or motion patterns. However, existing methods mainly focus on personalizing a single concept, either subject identity or motion pattern, limiting their effectiveness for multiple subjects with the desired motion patterns. To tackle this challenge, we propose a unified framework Video-Mage for video customization over both multiple subjects and their interactive motions. VideoMage employs subject and motion LoRAs to capture personalized content from user-provided images and videos, along with an appearance-agnostic motion learning approach to disentangle motion patterns from visual appearance. Furthermore, we develop a spatial-temporal composition scheme to guide interactions among subjects within the desired motion patterns. Extensive experiments demonstrate that VideoMage outperforms existing methods, generating coherent, user-controlled videos with consistent subject identities and interactions. Project Page: https://jasper0314-huang.github.io/videomage-customization/

LongSplat addresses critical challenges in novel view synthesis (NVS) from casually captured long videos characterized by irregular camera motion, unknown camera poses, and expansive scenes. Current methods often suffer from pose drift, inaccurate geometry initialization, and severe memory limitations. To address these issues, we introduce LongSplat, a robust unposed 3D Gaussian Splatting framework featuring: (1) Incremental Joint Optimization that concurrently optimizes camera poses and 3D Gaussians to avoid local minima and ensure global consistency; (2) a robust Pose Estimation Module leveraging learned 3D priors; and (3) an efficient Octree Anchor Formation mechanism that converts dense point clouds into anchors based on spatial density. Extensive experiments on challenging benchmarks demonstrate that LongSplat achieves state-of-the-art results, substantially improving rendering quality, pose accuracy, and computational efficiency compared to prior approaches. Project page: https://linjohnss.github.io/longsplat/

Vision-language-action (VLA) reasoning tasks require agents to interpret multimodal instructions, perform long-horizon planning, and act adaptively in dynamic environments. Existing approaches typically train VLA models in an end-to-end fashion, directly mapping inputs to actions without explicit reasoning, which hinders their ability to plan over multiple steps or adapt to complex task variations. In this paper, we propose ThinkAct, a dual-system framework that bridges high-level reasoning with low-level action execution via reinforced visual latent planning. ThinkAct trains a multimodal LLM to generate embodied reasoning plans guided by reinforcing action-aligned visual rewards based on goal completion and trajectory consistency. These reasoning plans are compressed into a visual plan latent that conditions a downstream action model for robust action execution on target environments. Extensive experiments on embodied reasoning and robot manipulation benchmarks demonstrate that ThinkAct enables few-shot adaptation, long-horizon planning, and self-correction behaviors in complex embodied AI tasks.

Federated Learning (FL) is an emerging paradigm that enables multiple users to collaboratively train a robust model in a privacy-preserving manner without sharing their private data. Most existing approaches of FL only consider traditional single-label image classification, ignoring the impact when transferring the task to multi-label image classification. Nevertheless, it is still challenging for FL to deal with user heterogeneity in their local data distribution in the real-world FL scenario, and this issue becomes even more severe in multi-label image classification. Inspired by the recent success of Transformers in centralized settings, we propose a novel FL framework for multi-label classification. Since partial label correlation may be observed by local clients during training, direct aggregation of locally updated models would not produce satisfactory performances. Thus, we propose a novel FL framework of Language-Guided Transformer (FedLGT) to tackle this challenging task, which aims to exploit and transfer knowledge across different clients for learning a robust global model. Through extensive experiments on various multi-label datasets (e.g., FLAIR, MS-COCO, etc.), we show that our FedLGT is able to achieve satisfactory performance and outperforms standard FL techniques under multi-label FL scenarios. Code is available at https://github.com/Jack24658735/FedLGT.

Natural Language Explanation (NLE) in vision and language tasks aims to provide human-understandable explanations for the associated decision-making process. In practice, one might encounter explanations which lack informativeness or contradict visual-grounded facts, known as implausibility and hallucination problems, respectively. To tackle these challenging issues, we consider the task of visual question answering (VQA) and introduce Rapper, a two-stage Reinforced Rationale-Prompted Paradigm. By knowledge distillation, the former stage of Rapper infuses rationale-prompting via large language models (LLMs), encouraging the rationales supported by language-based facts. As for the latter stage, a unique Reinforcement Learning from NLE Feedback (RLNF) is introduced for injecting visual facts into NLE generation. Finally, quantitative and qualitative experiments on two VL-NLE benchmarks show that Rapper surpasses state-of-the-art VQA-NLE methods while providing plausible and faithful NLE.

Federated learning (FL) emerges as a decentralized learning framework which trains models from multiple distributed clients without sharing their data to preserve privacy. Recently, large-scale pre-trained models (e.g., Vision Transformer) have shown a strong capability of deriving robust representations. However, the data heterogeneity among clients, the limited computation resources, and the communication bandwidth restrict the deployment of large-scale models in FL frameworks. To leverage robust representations from large-scale models while enabling efficient model personalization for heterogeneous clients, we propose a novel personalized FL framework of client-specific Prompt Generation (pFedPG), which learns to deploy a personalized prompt generator at the server for producing client-specific visual prompts that efficiently adapts frozen backbones to local data distributions. Our proposed framework jointly optimizes the stages of personalized prompt adaptation locally and personalized prompt generation globally. The former aims to train visual prompts that adapt foundation models to each client, while the latter observes local optimization directions to generate personalized prompts for all clients. Through extensive experiments on benchmark datasets, we show that our pFedPG is favorable against state-of-the-art personalized FL methods under various types of data heterogeneity, allowing computation and communication efficient model personalization.

While self-supervised learning has been shown to benefit a number of vision tasks, existing techniques mainly focus on image-level manipulation, which may not generalize well to downstream tasks at patch or pixel levels. Moreover, existing SSL methods might not sufficiently describe and associate the above representations within and across image scales. In this paper, we propose a Self-Supervised Pyramid Representation Learning (SS-PRL) framework. The proposed SS-PRL is designed to derive pyramid representations at patch levels via learning proper prototypes, with additional learners to observe and relate inherent semantic information within an image. In particular, we present a cross-scale patch-level correlation learning in SS-PRL, which allows the model to aggregate and associate information learned across patch scales. We show that, with our proposed SS-PRL for model pre-training, one can easily adapt and fine-tune the models for a variety of applications including multi-label classification, object detection, and instance segmentation.

Few-shot semantic segmentation addresses the learning task in which only few images with ground truth pixel-level labels are available for the novel classes of interest. One is typically required to collect a large mount of data (i.e., base classes) with such ground truth information, followed by meta-learning strategies to address the above learning task. When only image-level semantic labels can be observed during both training and testing, it is considered as an even more challenging task of weakly supervised few-shot semantic segmentation. To address this problem, we propose a novel meta-learning framework, which predicts pseudo pixel-level segmentation masks from a limited amount of data and their semantic labels. More importantly, our learning scheme further exploits the produced pixel-level information for query image inputs with segmentation guarantees. Thus, our proposed learning model can be viewed as a pixel-level meta-learner. Through extensive experiments on benchmark datasets, we show that our model achieves satisfactory performances under fully supervised settings, yet performs favorably against state-of-the-art methods under weakly supervised settings.

When translating text inputs into layouts or images, existing works typically require explicit descriptions of each object in a scene, including their spatial information or the associated relationships. To better exploit the text input, so that implicit objects or relationships can be properly inferred during layout generation, we propose a LayoutTransformer Network (LT-Net) in this paper. Given a scene-graph input, our LT-Net uniquely encodes the semantic features for exploiting their co-occurrences and implicit relationships. This allows one to manipulate conceptually diverse yet plausible layout outputs. Moreover, the decoder of our LT-Net translates the encoded contextual features into bounding boxes with self-supervised relation consistency preserved. By fitting their distributions to Gaussian mixture models, spatially-diverse layouts can be additionally produced by LT-Net. We conduct extensive experiments on the datasets of MS-COCO and Visual Genome, and confirm the effectiveness and plausibility of our LT-Net over recent layout generation models. Codes will be released at LayoutTransformer.

Few-shot classification aims to carry out classification given only few labeled examples for the categories of interest. Though several approaches have been proposed, most existing few-shot learning (FSL) models assume that base and novel classes are drawn from the same data domain. When it comes to recognizing novel-class data in an unseen domain, this becomes an even more challenging task of domain generalized few-shot classification. In this paper, we present a unique learning framework for domain-generalized few-shot classification, where base classes are from homogeneous multiple source domains, while novel classes to be recognized are from target domains which are not seen during training. By advancing meta-learning strategies, our learning framework exploits data across multiple source domains to capture domain-invariant features, with FSL ability introduced by metric-learning based mechanisms across support and query data. We conduct extensive experiments to verify the effectiveness of our proposed learning framework and show learning from small yet homogeneous source data is able to perform preferably against learning from large-scale one. Moreover, we provide insights into choices of backbone models for domain-generalized few-shot classification.

Domain generalization (DG) aims to transfer the learning task from a single or multiple source domains to unseen target domains. To extract and leverage the information which exhibits sufficient generalization ability, we propose a simple yet effective approach of Adversarial Teacher-Student Representation Learning, with the goal of deriving the domain generalizable representations via generating and exploring out-of-source data distributions. Our proposed framework advances Teacher-Student learning in an adversarial learning manner, which alternates between knowledge-distillation based representation learning and novel-domain data augmentation. The former progressively updates the teacher network for deriving domain-generalizable representations, while the latter synthesizes data out-of-source yet plausible distributions. Extensive image classification experiments on benchmark datasets in multiple and single source DG settings confirm that, our model exhibits sufficient generalization ability and performs favorably against state-of-the-art DG methods.

Human face reenactment aims at transferring motion patterns from one face (from a source-domain video) to an-other (in the target domain with the identity of interest).While recent works report impressive results, they are notable to handle multiple identities in a unified model. In this paper, we propose a unique network of CrossID-GAN to perform multi-ID face reenactment. Given a source-domain video with extracted facial landmarks and a target-domain image, our CrossID-GAN learns the identity-invariant motion patterns via the extracted landmarks and such information to produce the videos whose ID matches that of the target domain. Both supervised and unsupervised settings are proposed to train and guide our model during training.Our qualitative/quantitative results confirm the robustness and effectiveness of our model, with ablation studies confirming our network design.

Generating videos with content and motion variations is a challenging task in computer vision. While the recent development of GAN allows video generation from latent representations, it is not easy to produce videos with particular content of motion patterns of interest. In this paper, we propose Dual Motion Transfer GAN (Dual-MTGAN), which takes image and video data as inputs while learning disentangled content and motion representations. Our Dual-MTGAN is able to perform deterministic motion transfer and stochastic motion generation. Based on a given image, the former preserves the input content and transfers motion patterns observed from another video sequence, and the latter directly produces videos with plausible yet diverse motion patterns based on the input image. The proposed model is trained in an end-to-end manner, without the need to utilize pre-defined motion features like pose or facial landmarks. Our quantitative and qualitative results would confirm the effectiveness and robustness of our model in addressing such conditioned image-to-video tasks.

Learning interpretable data representation has been an active research topic in deep learning and computer vision. While representation disentanglement is an effective technique for addressing this task, existing works cannot easily handle the problems in which manipulating and recognizing data across multiple domains are desirable. In this paper, we present a unified network architecture of Multi-domain and Multi-modal Representation Disentangler (M2RD), with the goal of learning domain-invariant content representation with the associated domain-specific representation observed. By advancing adversarial learning and disentanglement techniques, the proposed model is able to perform continuous image manipulation across data domains with multiple modalities. More importantly, the resulting domain-invariant feature representation can be applied for unsupervised domain adaptation. Finally, our quantitative and qualitative results would confirm the effectiveness and robustness of the proposed model over state-of-the-art methods on the above tasks.

Video summarization still remains a challenging task. Due to sufficient video data on the Internet, such task draws significant attention in the vision community and benefits a wide range of applications, e.g., video retrieval, search, etc. To effectively perform video summarization by deriving the keyframes which represent the given input video, we propose a novel framework named Hierarchical Multi-Attention Network (H-MAN) which comprises the shot-level reconstruction model and multi-head attention model. While our designed attention model is two-stage hierarchical structure for producing various attention maps, we are among the first to utilize the multi-attention mechanism in the video summarization task, which brings improved performance. The quantitative and qualitative results demonstrate the effectiveness of our model, which performs favorably against state-of-the-art approaches.