Video-based human pose estimation has long been a nontrivial task due to its dynamic nature and challenging detection scenarios such as occlusion and defocus. Inspired by the success of diffusion models, researchers have applied them to video pose estimation, outperforming traditional joint detection methods. However, existing diffusion model-based methods still face challenges like slow convergence and unstable pose generation. To tackle these issues, we propose DiffusionPose, a novel framework for video pose estimation that integrates diffusion models with optimization strategies: (1) We combine the emerging Mamba with Transformers to balance global and local spatio-temporal modeling. (2) We integrate Markov Random Fields into the reverse diffusion process to enhance the denoising of pose heatmaps, particularly addressing the issue of confused generation of occluded joints. (3) We mathematically formulate a Markov objective to supervise the heatmap denoising process, enabling the model to generate anatomically plausible skeletons. Our method achieves state-of-the-art performance on three large-scale benchmark datasets. Interestingly, it shows surprising robustness in challenging video scenarios, improving the accuracy of the most difficult ankle joint by 16.9% compared to the previous best diffusion model-based method on the Challenging-PoseTrack dataset.

Video-based human pose estimation aims to localize keypoints across frames, enabling robust analysis of human motion in applications such as sports, surveillance, and healthcare. However, existing methods rely solely on visual cues, limiting their robustness in complex scenes involving occlusion, motion blur, or poor lighting. In contrast, dual coding theory from psychology suggests that human cognition is inherently multimodal: we learn by integrating visual perception with linguistic context to form structured, semantic understandings of the world. Visual input provides concrete spatiotemporal grounding, while language offers symbolic abstraction that enhances reasoning and generalization. Motivated by this cognitive principle, we present the first framework that explicitly incorporates language as an auxiliary modality to enhance video-based pose estimation. To address the lack of paired video-text datasets, we first employ a Multimodal Large Language Model (MLLM) to generate textual descriptions of human interactions from videos. We then propose a novel coarse-to-fine multimodal alignment pipeline: a cross-modal semantic interaction module establishes initial grounding between spatiotemporal visual features and textual embeddings, while an optimal transport-based feature matching mechanism enforces fine-grained, geometry-aware alignment. This cognitively inspired design enables more accurate and robust pose estimation, especially in visually challenging scenes like occlusion and motion blur. Extensive experiments on three benchmarks confirm that our method consistently outperforms state-of-the-art approaches.

Video-based human pose estimation has vast applications such as action recognition, sports analytics, and crime detection. However, this task is challenging as it involves interpreting both spatial context and temporal dynamics to accurately localize human anatomical keypoints in video sequences. Current approaches, often based on attention mechanisms, perform well but struggle in challenging scenarios like rapid motion and pose occlusion. We attribute these failures to two fundamental limitations: spatial uniformity, where models indiscriminately assign attention to both joint-relevant features and background clutter, thereby introducing spatial noise; and temporal rigidity, an inability to adapt to large joint displacements, resulting in severe feature misalignment during rapid motion. To overcome these challenges, we introduce PSTPose, a novel progressive spatiotemporal refinement framework. Specifically, to address the spatial uniformity problem, we propose a Discriminative Feature Enhancement (DFE) module that emphasizes joint-relevant features and a Feature Cluster Grouping (FCG) module that forms compact, semantically meaningful regions. For the temporal rigidity problem, we introduce a Deformable Spatiotemporal Fusion (DSF) module that adaptively aligns features across consecutive frames via deformation-aware sampling. This design ensures robust keypoint localization, particularly in cluttered and dynamic scenes. Extensive experiments on three large-scale benchmarks, PoseTrack2017, PoseTrack2018, PoseTrack21, demonstrate that PSTPose establishes a new state-of-the-art.

Advanced deepfake technologies are blurring the lines between real and fake, presenting both revolutionary opportunities and alarming threats. While it unlocks novel applications in fields like entertainment and education, its malicious use has sparked urgent ethical and societal concerns ranging fromidentity theftto thedissemination of misinformation. To tackle these challenges, feature analysis using frequency features has emerged as a promising direction for deepfake detection. However, one aspect that has been overlooked so far is that existing methods tend to concentrate on one or a few specific frequency domains, which risks overfitting to particular artifacts and significantly undermines their robustness when facing diverse forgery patterns. Another underexplored aspect we observe is that different features often attend to the same forged region, resulting in redundant feature representations and limiting the diversity of the extracted clues. This may undermine the ability of a model to capture complementary information across different facets, thereby compromising its generalization capability to diverse manipulations. In this paper, we seek to tackle these challenges from two aspects: (1) we propose a triple-branch network that jointly captures spatial and frequency features by learning from both original image and image reconstructed by different frequency channels, and (2) we mathematically derive feature decoupling and fusion losses grounded in the mutual information theory, which enhances the model to focus on task-relevant features across the original image and the image reconstructed by different frequency channels. Extensive experiments onsixlarge-scale benchmark datasets demonstrate that our method consistently achieves state-of-the-art performance. Our code is released athttps://github.com/injooker/Unveiling_Deepfake.

Video-based human pose estimation has long been a fundamental yet challenging problem in computer vision. Previous studies focus on spatio-temporal modeling through the enhancement of architecture design and optimization strategies. However, they overlook the causal relationships in the joints, leading to models that may be overly tailored and thus estimate poorly to challenging scenes. Therefore, adequate causal reasoning capability, coupled with good interpretability of model, are both indispensable and prerequisite for achieving reliable results. In this paper, we pioneer a causal perspective on pose estimation and introduce a causal-inspired multitask learning framework, consisting of two stages. In the first stage, we try to endow the model with causal spatio-temporal modeling ability by introducing two self-supervision auxiliary tasks. Specifically, these auxiliary tasks enable the network to infer challenging keypoints based on observed keypoint information, thereby imbuing causal reasoning capabilities into the model and making it robust to challenging scenes. In the second stage, we argue that not all feature tokens contribute equally to pose estimation. Prioritizing causal (keypoint-relevant) tokens is crucial to achieve reliable results, which could improve the interpretability of the model. To this end, we propose a Token Causal Importance Selection module to identify the causal tokens and non-causal tokens (e.g., background and objects). Additionally, non-causal tokens could provide potentially beneficial cues but may be redundant. We further introduce a non-causal tokens clustering module to merge the similar non-causal tokens. Extensive experiments show that our method outperforms state-of-the-art methods on three large-scale benchmark datasets.

Human pose estimation has given rise to a broad spectrum of novel and compelling applications, including action recognition, sports analysis, as well as surveillance. However, accurate video pose estimation remains an open challenge. One aspect that has been overlooked so far is that existing methods learn motion clues from all pixels rather than focusing on the target human body, making them easily misled and disrupted by unimportant information such as background changes or movements of other people. Additionally, while the current Transformer-based pose estimation methods has demonstrated impressive performance with global modeling, they struggle with local context perception and precise positional identification. In this paper, we try to tackle these challenges from three aspects: (1) We propose a bilayer Human-Keypoint Mask module that performs coarse-to-fine visual token refinement, which gradually zooms in on the target human body and keypoints while masking out unimportant figure regions. (2) We further introduce a novel deformable cross attention mechanism and a bidirectional separation strategy to adaptively aggregate spatial and temporal motion clues from constrained surrounding contexts. (3) We mathematically formulate the deformable cross attention, constraining that the model focuses solely on the regions centered at the target person body. Empirically, our method achieves state-of-the-art performance on three large-scale benchmark datasets. A remarkable highlight is that our method achieves an 84.8 mean Average Precision (mAP) on the challenging wrist joint, which significantly outperforms the 81.5 mAP achieved by the current state-of-the-art method on the PoseTrack2017 dataset.

Human pose estimation in videos remains a challenge, largely due to the reliance on extensive manual annotation of large datasets, which is expensive and labor-intensive. Furthermore, existing approaches often struggle to capture long-range temporal dependencies and overlook the complementary relationship between temporal pose heatmaps and visual features. To address these limitations, we introduce STDPose, a novel framework that enhances human pose estimation by learning spatiotemporal dynamics in sparsely-labeled videos. STDPose incorporates two key innovations: 1) A novel Dynamic-Aware Mask to capture long-range motion context, allowing for a nuanced understanding of pose changes. 2) A system for encoding and aggregating spatiotemporal representations and motion dynamics to effectively model spatiotemporal relationships, improving the accuracy and robustness of pose estimation. STDPose establishes a new performance benchmark for both video pose propagation (i.e., propagating pose annotations from labeled frames to unlabeled frames) and pose estimation tasks, across three large-scale evaluation datasets. Additionally, utilizing pseudo-labels generated by pose propagation, STDPose achieves competitive performance with only 26.7% labeled data.

Human pose estimation, with its broad applications in action recognition and motion capture, has experienced significant advancements. However, current Transformer-based methods for video pose estimation often face challenges in managing redundant temporal information and achieving fine-grained perception because they only focus on processing low-resolution features. To address these challenges, we propose a novel multi-scale resolution framework that encodes spatiotemporal representations at varying granularities and executes fine-grained perception compensation. Furthermore, we employ a density peaks clustering method to dynamically identify and prioritize tokens that offer important semantic information. This strategy effectively prunes redundant feature tokens, especially those arising from multi-frame features, thereby optimizing computational efficiency without sacrificing semantic richness. Empirically, it sets new benchmarks for both performance and efficiency on three large-scale datasets. Our method achieves a 93.8% improvement in inference speed compared to the baseline, while also enhancing pose estimation accuracy, reaching 87.4 mAP on the PoseTrack2017 dataset.

With the ongoing development of public video surveillance technology, accurate human pose estimation is becoming increasingly important in urban administration and law enforcement. However, existing methods rely on large-scale dense annotations, which are labor-intensive and time-consuming. To tackle this, we propose SparsePose which leverages training videos with sparse annotations (labeled every k frames) to learn to propagate temporal poses that help to estimate the poses in unlabeled frames. Technically, we engage in a novel dual-branch architecture that combines 1) pose forecasting of the consecutive neighboring frames with 2) visual clues of the current frame and the nearest labeled frames. We theoretically derive the intrabranch and interbranch mutual information loss to supervise that maximized pose-relevant features are extracted from the current frame and different branches complement each other to approach precise pose estimation. Additionally, we propose a diffusion generative enhancement, which improves the robustness of the model to challenging scenes from the perspective of diversity. Empirical results show that our method significantly outperforms the state-of-the-art methods in sparsely labeled pose estimation on three benchmark datasets.

Human pose estimation in videos has long been a compelling yet challenging task within the realm of computer vision. Nevertheless, this task remains difficult because of the complex video scenes, such as video defocus and self-occlusion. Recent methods strive to integrate multi-frame visual features generated by a backbone network for pose estimation. However, they often ignore the useful joint information encoded in the initial heatmap, which is a by-product of the backbone generation. Comparatively, methods that attempt to refine the initial heatmap fail to consider any spatio-temporal motion features. As a result, the performance of existing methods for pose estimation falls short due to the lack of ability to leverage both local joint (heatmap) information and global motion (feature) dynamics.

Human motion copy is an intriguing yet challenging task in artificial intelligence and computer vision, which strives to generate a fake video of a target person performing the motion of a source person. The problem is inherently challenging due to the subtle human-body texture details to be generated and the temporal consistency to be considered. Existing approaches typically adopt a conventional GAN with an L1 or L2 loss to produce the target fake video, which intrinsically necessitates a large number of training samples that are challenging to acquire. Meanwhile, current methods still have difficulties in attaining realistic image details and temporal consistency, which unfortunately can be easily perceived by human observers. Motivated by this, we try to tackle the issues from three aspects: (1) We constrain pose-to-appearance generation with a perceptual loss and a theoretically motivated Gromov-Wasserstein loss to bridge the gap between pose and appearance. (2) We present an episodic memory module in the pose-to-appearance generation to propel continuous learning that helps the model learn from its past poor generations. We also utilize geometrical cues of the face to optimize facial details and refine each key body part with a dedicated local GAN. (3) We advocate generating the foreground in a sequence-to-sequence manner rather than a single-frame manner, explicitly enforcing temporal inconsistency. Empirical results on five datasets,iPER, ComplexMotion, SoloDance, Fish, and Mouse datasets, demonstrate that our method is capable of generating realistic target videos while precisely copying motion from a source video. Our method significantly outperforms state-of-the-art approaches and gains 7.2% and 12.4% improvements in PSNR and FID respectively.

One compelling application of artificial intelligence is to generate a video of a target person performing arbitrary desired motion (from a source person). While the state-of-the-art methods are able to synthesize a video demonstrating similar broad stroke motion details, they are generally lacking in texture details. A pertinent manifestation appears as distorted face, feet, and hands, and such flaws are very sensitively perceived by human observers. Furthermore, current methods typically employ GANs with a L2 loss to assess the authenticity of the generated videos, inherently requiring a large amount of training samples to learn the texture details for adequate video generation. In this work, we tackle these challenges from three aspects: 1) We disentangle each video frame into foreground (the person) and background, focusing on generating the foreground to reduce the underlying dimension of the network output. 2) We propose a theoretically motivated Gromov-Wasserstein loss that facilitates learning the mapping from a pose to a foreground image. 3) To enhance texture details, we encode facial features with geometric guidance and employ local GANs to refine the face, feet, and hands. Extensive experiments show that our method is able to generate realistic target person videos, faithfully copying complex motions from a source person. Our code and datasets are released at https://github.com/Sifann/FakeMotion.

Multi-frame human pose estimation is at the core of many computer vision tasks. Although state-of-the-art approaches have demonstrated remarkable results for human pose estimation on static images, their performances inevitably come short when being applied to videos. A central issue lies in the visual degeneration of video frames induced by rapid motion and pose occlusion in dynamic environments. This problem, by nature, is insurmountable for a single frame. Therefore, incorporating complementary visual cues from other video frames becomes an intuitive paradigm. Current state-of-the-art methods usually leverage information from adjacent frames, which unfortunately place excessive focus on only the temporally nearby frames. In this paper, we argue that combining global semantically similar information and local temporal visual context will deliver more comprehensive and more robust representations for human pose estimation. Towards this end, we present an effective framework, namely global-local enhanced pose estimation ( GLPose ) network. Our framework consists of a feature processing module that conditionally incorporates global semantic information and local visual context to generate a robust human representation and a feature enhancement module that excavates complementary information from this aggregated representation to enhance keyframe features for precise estimation. We empirically find that the proposed GLpose outperforms existing methods by a large margin and achieves new state-of-the-art results on large benchmark datasets.