We introduce GazeD, a new 3D gaze estimation method that jointly provides 3D gaze and human pose from a single RGB image. Leveraging the ability of diffusion models to deal with uncertainty, it generates multiple plausible 3D gaze and pose hypotheses based on the 2D context information extracted from the input image. Specifically, we condition the denoising process on the 2D pose, the surroundings of the subject, and the context of the scene. With GazeD we also introduce a novel way of representing the 3D gaze by positioning it as an additional body joint at a fixed distance from the eyes. The rationale is that the gaze is usually closely related to the pose, and thus it can benefit from being jointly denoised during the diffusion process. Evaluations across three benchmark datasets demonstrate that GazeD achieves state-of-the-art performance in 3D gaze estimation, even surpassing methods that rely on temporal information. Project details will be available at https://aimagelab.ing.unimore.it/go/gazed

Forecasting abnormal human behavior (AHB) in unconstrained real-world environments is critical for enabling proactive safety interventions. Unlike short-term anomaly detection, long-horizon forecasting offers a vital reaction window but remains underexplored due to three core challenges: (i) noisy, complex human–agent interactions; (ii) weak temporal coupling between normal observations and distant anomalies; and (iii) data scarcity limiting the scalability of autoregressive models. To address these, we propose ${{\mathcal{D}}^3}{\mathcal{P}}$ (Denoise, Divide, Distill, and Predict), a novel encoder–decoder framework that bridges denoised pasts with distilled autoregressive futures. Our Differential Past Encoder (DiPE) disentangles scene-level and object-level dynamics via differential attention, suppressing irrelevant interactions and enhancing discriminative cues. The Distilled Future Auto-Regressive Decoder (D-FAD) adopts a divide-and-conquer strategy, segmenting future queries into temporal chunks for sequential prediction, while leveraging distillation to balance robustness and latency. We validate our approach on the AHB-F benchmark, the only dataset dedicated to abnormal behavior forecasting, and further integrate D-FAD with several state-of-the-art methods. In all cases, our framework consistently outperforms prior work in both forecasting accuracy and computational efficiency.

Weakly-supervised methods for video anomaly detection (VAD) are conventionally based merely on RGB spatio-temporal features, which continues to limit their reliability in real-world scenarios. This is due to the fact that RGB-features are not sufficiently distinctive in setting apart categories such as shoplifting from visually similar events. Therefore, towards robust complex real-world VAD, it is essential to augment RGB spatio-temporal features by additional modalities. Motivated by this, we introduce the Poly-modal Induced framework for VAD: "PI-VAD" (or π-VAD), a novel approach that augments RGB representations by five additional modalities. Specifically, the modalities include sensitivity to fine-grained motion (Pose), three dimensional scene and entity representation (Depth), surrounding objects (Panoptic masks), global motion (optical flow), as well as language cues (VLM). Each modality represents an axis of a polygon, streamlined to add salient cues to RGB. π-VAD includes two plug-in modules, namely Pseudo-modality Generation module and Cross Modal Induction module, which generate modality-specific prototypical representation and, thereby, induce multi-modal information into RGB cues. These modules operate by performing anomaly-aware auxiliary tasks and necessitate five modality backbones – only during training. Notably, π-VAD achieves state-of-the-art accuracy on three prominent VAD datasets encompassing real-world scenarios, without requiring the computational overhead of five modality backbones at inference.

Video Anomaly Detection (VAD) is a challenging task due to the variability of anomalous events and the limited availability of labeled data. Under the Weakly-Supervised VAD (WSVAD) paradigm, only video-level labels are provided during training, while predictions are made at the frame level. Although state-of-the-art models perform well on simple anomalies (e.g., explosions), they struggle with complex real-world events (e.g., shoplifting). This difficulty stems from two key issues: (1) the inability of current models to address the diversity of anomaly types, as they process all categories with a shared model, overlooking category-specific features; and (2) the weak supervision signal, which lacks precise temporal information, limiting the ability to capture nuanced anomalous patterns blended with normal events. To address these challenges, we propose Gaussian Splatting-guided Mixture of Experts (GS-MoE), a novel framework that employs a set of expert models, each specialized in capturing specific anomaly types. These experts are guided by a temporal Gaussian splatting loss, enabling the model to leverage temporal consistency and enhance weak supervision. The Gaussian splatting approach encourages a more precise and comprehensive representation of anomalies by focusing on temporal segments most likely to contain abnormal events. The predictions from these specialized experts are integrated through a mixture-of-experts mechanism to model complex relationships across diverse anomaly patterns. Our approach achieves state-of-the-art performance, with a 91.58% AUC on the UCF-Crime dataset, and demonstrates superior results on XD-Violence and MSAD datasets. By leveraging category-specific expertise and temporal guidance, GS-MoE sets a new benchmark for VAD under weak supervision.

Forecasting Abnormal Human Behavior (AHB) aims to predict unusual behavior in advance by analyzing early patterns of normal human interactions. Unlike typical action prediction methods, this task focuses on observing only normal interactions to predict both, short and long term future abnormal behavior. Despite its affirmative impact on society, AHB prediction remains under-explored in current research. This is primarily due to the challenges involved in anticipating complex human behaviors and interactions with surrounding agents in real-world situations. Further, there exists an underlying uncertainty between the early normal patterns and the future abnormal behavior, thereby making the prediction harder. To address these challenges, we introduce a novel transformer model that improves early interaction modeling by accounting for uncertainties in both, observations and future outcomes. To the best of our knowledge, we are the first to explore the task. Therefore, we present a new comprehensive dataset referred to as “AHB-F”††Code, Models, Dataset: https://github.com/snehashismajhi/AHB-F, which features real-world scenarios with complex human interactions. The AHB-F has a deterministic evaluation protocol that ensures only normal frames to be observed for long and short term future prediction. We extensively evaluate and compare competitive action anticipation methods on our benchmark. Our results show that our method consistently outperforms existing action anticipation approaches, both in quantitative and qualitative evaluations.

Estimating 6D object poses is a major challenge in 3D computer vision. Building on successful instance-level approaches, research is shifting towards category-level pose estimation for practical applications. Current category-level datasets, however, fall short in annotation quality and pose variety. Addressing this, we introduce HouseCat6D, a new category-level 6D pose dataset. It features 1) multi-modality with Polarimetric RGB and Depth (RGBD+P), 2) encompasses 194 diverse objects across 10 household cat-egories, including two photometrically challenging ones, and 3) provides high-quality pose annotations with an error range of only 1.35 mm to 1.74 mm. The dataset also includes 4) 41 large-scale scenes with comprehensive view-point and occlusion coverage,5) a checkerboard-free en-vironment, and 6) dense 6D parallel-jaw robotic grasp annotations. Additionally, we present benchmark results for leading category-level pose estimation networks.

Video anomaly detection in real-world scenarios is challenging due to the complex temporal blending of long and short-length anomalies with normal ones. Further, it is more difficult to detect those due to : (i) Distinctive features characterizing the short and long anomalies with sharp and progressive temporal cues respectively; (ii) Lack of precise temporal information (i.e. weak-supervision) limits the temporal dynamics modeling of anomalies from normal events. In this paper, we propose a novel ‘temporal transformer’ framework for weakly-supervised anomaly detection: OE-CTST†. The proposed framework has two major components: (i) Outlier Embedder (OE) and (ii) Cross Temporal Scale Transformer (CTST). First, OE generates anomaly-aware temporal position encoding to allow the transformer to effectively model the temporal dynamics among the anomalies and normal events. Second, CTST encodes the cross-correlation between multi-temporal scale features to benefit short and long length anomalies by modeling the global temporal relations. The proposed OE-CTST is validated on three publicly available datasets i.e. UCF-Crime, XD-Violence, and IITB-Corridor, outperforming recently reported state-of-the-art approaches.

Self-supervised video representation learning aimed at maximizing similarity between different temporal segments of one video, in order to enforce feature persistence over time. This leads to loss of pertinent information related to temporal relationships, rendering actions such as `enter' and `leave' to be indistinguishable. To mitigate this limitation, we propose Latent Time Navigation (LTN), a time parameterized contrastive learning strategy that is streamlined to capture fine-grained motions. Specifically, we maximize the representation similarity between different video segments from one video, while maintaining their representations time-aware along a subspace of the latent representation code including an orthogonal basis to represent temporal changes. Our extensive experimental analysis suggests that learning video representations by LTN consistently improves performance of action classification in fine-grained and human-oriented tasks (e.g., on Toyota Smarthome dataset). In addition, we demonstrate that our proposed model, when pre-trained on Kinetics-400, generalizes well onto the unseen real world video benchmark datasets UCF101 and HMDB51, achieving state-of-the-art performance in action recognition.

Skeleton-based action segmentation requires recognizing composable actions in untrimmed videos. Current approaches decouple this problem by first extracting local visual features from skeleton sequences and then processing them by a temporal model to classify frame-wise actions. However, their performances remain limited as the visual features cannot sufficiently express composable actions. In this context, we propose Latent Action Composition (LAC)1, a novel self-supervised framework aiming at learning from synthesized composable motions for skeleton-based action segmentation. LAC is composed of a novel generation module towards synthesizing new sequences. Specifically, we design a linear latent space in the generator to represent primitive motion. New composed motions can be synthe-sized by simply performing arithmetic operations on latent representations of multiple input skeleton sequences. LAC leverages such synthesized sequences, which have large diversity and complexity, for learning visual representations of skeletons in both sequence and frame spaces via contrastive learning. The resulting visual encoder has a high expressive power and can be effectively transferred onto action segmentation tasks by end-to-end fine-tuning without the need for additional temporal models. We conduct a study focusing on transfer-learning and we show that representations learned from pre-trained LAC outperform the state-of-the-art by a large margin on TSU, Charades, PKU-MMD datasets.

Designing activity detection systems that can be successfully deployed in daily-living environments requires datasets that pose the challenges typical of real-world scenarios. In this paper, we introduce a new untrimmed daily-living dataset that features several real-world challenges: Toyota Smarthome Untrimmed (TSU). TSU contains a wide variety of activities performed in a spontaneous manner. The dataset contains dense annotations including elementary, composite activities and activities involving interactions with objects. We provide an analysis of the real-world challenges featured by our dataset, highlighting the open issues for detection algorithms. We show that current state-of-the-art methods fail to achieve satisfactory performance on the TSU dataset. Therefore, we propose a new baseline method for activity detection to tackle the novel challenges provided by our dataset. This method leverages one modality (i.e. optic flow) to generate the attention weights to guide another modality (i.e RGB) to better detect the activity boundaries. This is particularly beneficial to detect activities characterized by high temporal variance. We show that the method we propose outperforms state-of-the-art methods on TSU and on another popular challenging dataset, Charades.

Object pose estimation is crucial for robotic applications and augmented reality. Beyond instance level 6D object pose estimation methods, estimating category-level pose and shape has become a promising trend. As such, a new research field needs to be supported by well-designed datasets. To provide a benchmark with high-quality ground truth annotations to the community, we introduce a multimodal dataset for category-level object pose estimation with photometrically challenging objects termed PhoCaL. PhoCaL comprises 60 high quality 3D models of household objects over 8 categories including highly reflective, transparent and symmetric objects. We developed a novel robot-supported multi-modal (RGB, depth, polarisation) data acquisition and annotation process. It ensures sub-millimeter accuracy of the pose for opaque textured, shiny and transparent objects, no motion blur and perfect camera synchronisation. To set a benchmark for our dataset, state-of-the-art RGB-D and monocular RGB methods are evaluated on the challenging scenes of PhoCaL.

Action recognition based on human pose has witnessed increasing attention due to its robustness to changes in appearances, environments, and view-points. Despite associated progress, one remaining challenge has to do with occlusion in real-world videos that hinders the visibility of all joints. Such occlusion impedes representation of such scenes by models that have been trained on full-body pose data, obtained in laboratory conditions with specific sensors. To address this, as a first contribution, we introduce OR- VPE, a novel video pose embedding network that is streamlined to learn an occlusion-robust representation for pose sequences in videos. In order to enable our embedding network to handle partially visible joints, we propose to incorporate a sub-graph data augmentation mechanism during training, which simulates occlusions, into a video pose encoder based on Graph Convolutional Networks (GCNs). As a second contribution, we apply a contrastive learning module to train the video pose representation in a self-supervised manner without the necessity of action annotations. This is achieved by maximizing the mutual information of the same pose sequence pruned into different spatio-temporal subgraphs. Experimental analyses show that compared to training the same encoder from scratch, our proposed OR-VPE, with pre-training on a large-scale dataset, NTU-RGB+D 120, improves the performance of the downstream action classification on Toyota Smarthome, N-UCLA and Penn Action datasets.

The ability to successfully grasp objects is crucial in robotics, as it enables several interactive downstream applications. To this end, most approaches either compute the full 6D pose for the object of interest or learn to predict a set of grasping points. While the former approaches do not scale well to multiple object instances or classes yet, the latter require large annotated datasets and are hampered by their poor generalization capabilities to new geometries. To overcome these shortcomings, we propose to teach a robot how to grasp an object with a simple and short human demonstration. Hence, our approach neither requires many annotated images nor is it restricted to a specific geometry. We first present a small sequence of RGB-D images displaying a human-object interaction. This sequence is then leveraged to build associated hand and object meshes that represent the depicted interaction. Subsequently, we complete missing parts of the reconstructed object shape and estimate the relative transformation between the reconstruction and the visible object in the scene. Finally, we transfer the a-priori knowledge from the relative pose between object and human hand with the estimate of the current object pose in the scene into necessary grasping instructions for the robot. Exhaustive evaluations with Toyota’s Human Support Robot (HSR) in real and synthetic environments demonstrate the applicability of our proposed methodology and its advantage in comparison to previous approaches.

Handling long and complex temporal information is an important challenge for action detection tasks. This challenge is further aggravated by densely distributed actions in untrimmed videos. Previous action detection methods fail in selecting the key temporal information in long videos. To this end, we introduce the Dilated Attention Layer (DAL). Compared to previous temporal convolution layer, DAL allocates attentional weights to local frames in the kernel, which enables it to learn better local representation across time. Furthermore, we introduce Pyramid Dilated Attention Network (PDAN) which is built upon DAL. With the help of multiple DALs with different dilation rates, PDAN can model short-term and long-term temporal relations simultaneously by focusing on local segments at the level of low and high temporal receptive fields. This property enables PDAN to handle complex temporal relations between different action instances in long untrimmed videos. To corroborate the effectiveness and robustness of our method, we evaluate it on three densely annotated, multi-label datasets: Mul-tiTHUMOS, Charades and Toyota Smarthome Untrimmed (TSU) dataset. PDAN is able to outperform previous state-of-the-art methods on all these datasets."Time abides long enough for those who make use of it.

In this paper, we address the detection of daily living activities in long-term untrimmed videos. The detection of daily living activities is challenging due to their long temporal components, low inter-class variation and high intra-class variation. To tackle these challenges, recent approaches based on Temporal Convolutional Networks (TCNs) have been proposed. Such methods can capture long-term temporal patterns using a hierarchy of temporal convolutional filters, pooling and up sampling steps. However, as one of the important features of convolutional networks, TCNs process a local neighborhood across time which leads to inefficiency in modeling the long-range dependencies between these temporal patterns of the video. In this paper, we propose Self-Attention - Temporal Convolutional Network (SA-TCN), which is able to capture both complex activity patterns and their dependencies within long-term untrimmed videos. We evaluate our proposed model on DAily Home LIfe Activity Dataset (DAHLIA) and Breakfast datasets. Our proposed method achieves state-of-the-art performance on both DAHLIA and Breakfast dataset.

The performance of deep neural networks is strongly influenced by the quantity and quality of annotated data. Most of the large activity recognition datasets consist of data sourced from the web, which does not reflect challenges that exist in activities of daily living. In this paper, we introduce a large real-world video dataset for activities of daily living: Toyota Smarthome. The dataset consists of 16K RGB+D clips of 31 activity classes, performed by seniors in a smarthome. Unlike previous datasets, videos were fully unscripted. As a result, the dataset poses several challenges: high intra-class variation, high class imbalance, simple and composite activities, and activities with similar motion and variable duration. Activities were annotated with both coarse and fine-grained labels. These characteristics differentiate Toyota Smarthome from other datasets for activity recognition. As recent activity recognition approaches fail to address the challenges posed by Toyota Smarthome, we present a novel activity recognition method with attention mechanism. We propose a pose driven spatio-temporal attention mechanism through 3D ConvNets. We show that our novel method outperforms state-of-the-art methods on benchmark datasets, as well as on the Toyota Smarthome dataset. We release the dataset for research use.