Mitigating the risks from frontier AI systems requires up-to-date and reliable information about those systems. Organizations that develop and deploy frontier systems have significant access to such information. By reporting safety-critical information to actors in government, industry, and civil society, these organizations could improve visibility into new and emerging risks posed by frontier systems. Equipped with this information, developers could make better informed decisions on risk management, while policymakers could design more targeted and robust regulatory infrastructure. We outline the key features of responsible reporting and propose mechanisms for implementing them in practice.

Laura Weidinger, John F J Mellor, Bernat Guillén Pegueroles, Nahema Marchal, Ravin Kumar, Kristian Lum, Canfer Akbulut, Mark Diaz, A. Stevie Bergman, Mikel D. Rodriguez, Verena Rieser, William Isaac. Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing. 2024.

In this study, the authors present a learning‐free method for inferring kinematically plausible three‐dimensional (3D) human body poses contextualised in a predefined 3D world, given a set of 2D body features extracted from monocular images. This contextualisation has the advantage of providing further semantic information about the observed scene. Their method consists of two main steps. Initially, the camera parameters are obtained by adjusting the reference floor of the predefined 3D world to four key‐points in the image. Then, the person's body part lengths and pose are estimated by fitting a parametrised multi‐body 3D kinematic model to 2D image body features, which can be located by state‐of‐the‐art body part detectors. The adjustment is carried out by a hierarchical optimisation procedure, where the model's scale variations are considered first and then the body part lengths are refined. At each iteration, tentative poses are inferred by a combination of efficient perspective‐n‐point camera pose estimation and constrained viewpoint‐dependent inverse kinematics. Experimental results show that their method obtains good results in terms of accuracy with respect to state‐of‐the‐art alternatives, but without the need of learning 2D/3D mapping models from training data. Their method works efficiently, allowing its integration in video soft sensing systems.

We present a demonstration of a multi-modal 3D capturing platform coupled to a motion comparison system. This work is focused on the preservation of Traditional Sports and Games, namely the Gaelic sports from Ireland and Basque sports from France and Spain. Users can learn, compare and compete in the performance of sporting gestures and compare themselves to real athletes. Our online gesture database provides a way to preserve and display a wide range of sporting gestures. The capturing devices utilised are Kinect 2 sensors and wearable inertial sensors, where the number required varies based on the requested scenario. The fusion of these two capture modalities, coupled to our inverse kinematic algorithm, allow us to synthesize a fluid and reliable 3D model of the user gestures over time. Our novel comparison algorithms provide the user with a performance score and a set of comparison curves (i.e. joint angles and angular velocities), providing a precise and valuable feedback for coaches and players.

How should a video be represented? We propose a new representation for videos based on mid-level discriminative spatio-temporal patches. These spatio-temporal patches might correspond to a primitive human action, a semantic object, or perhaps a random but informative spatio-temporal patch in the video. What defines these spatio-temporal patches is their discriminative and representative properties. We automatically mine these patches from hundreds of training videos and experimentally demonstrate that these patches establish correspondence across videos and align the videos for label transfer techniques. Furthermore, these patches can be used as a discriminative vocabulary for action classification where they demonstrate state-of-the-art performance on UCF50 and Olympics datasets.

We address the problem of person detection and tracking in crowded video scenes. While the detection of individual objects has been improved significantly over the recent years, crowd scenes remain particularly challenging for the detection and tracking tasks due to heavy occlusions, high person densities and significant variation in people's appearance. To address these challenges, we propose to leverage information on the global structure of the scene and to resolve all detections jointly. In particular, we explore constraints imposed by the crowd density and formulate person detection as the optimization of a joint energy function combining crowd density estimation and the localization of individual people. We demonstrate how the optimization of such an energy function significantly improves person detection and tracking in crowds. We validate our approach on a challenging video dataset of crowded scenes.

In this work we present a new crowd analysis algorithm powered by behavior priors that are learned on a large database of crowd videos gathered from the Internet. The algorithm works by first learning a set of crowd behavior priors off-line. During testing, crowd patches are matched to the database and behavior priors are transferred. We adhere to the insight that despite the fact that the entire space of possible crowd behaviors is infinite, the space of distinguishable crowd motion patterns may not be all that large. For many individuals in a crowd, we are able to find analogous crowd patches in our database which contain similar patterns of behavior that can effectively act as priors to constrain the difficult task of tracking an individual in a crowd. Our algorithm is data-driven and, unlike some crowd characterization methods, does not require us to have seen the test video beforehand. It performs like state-of-the-art methods for tracking people having common crowd behaviors and outperforms the methods when the tracked individual behaves in an unusual way.

This paper presents a target tracking framework for unstructured crowded scenes. Unstructured crowded scenes are defined as those scenes where the motion of a crowd appears to be random with different participants moving in different directions over time. This means each spatial location in such scenes supports more than one, or multi-modal, crowd behavior. The case of tracking in structured crowded scenes, where the crowd moves coherently in a common direction, and the direction of motion does not vary over time, was previously handled in. In this work, we propose to model various crowd behavior (or motion) modalities at different locations of the scene by employing Correlated Topic Model (CTM) of. In our construction, words correspond to low level quantized motion features and topics correspond to crowd behaviors. It is then assumed that motion at each location in an unstructured crowd scene is generated by a set of behavior proportions, where behaviors represent distributions over low-level motion features. This way any one location in the scene may support multiple crowd behavior modalities and can be used as prior information for tracking. Our approach enables us to model a diverse set of unstructured crowd domains, which range from cluttered time-lapse microscopy videos of cell populations in vitro, to footage of crowded sporting events.