Related papers: Play Fair: Frame Attributions in Video Models

Explainability and fairness have mainly been considered separately, with recent exceptions trying the explain the sources of unfairness. This paper shows that the Shapley value can be used to both define and explain unfairness, under…

As an emerging field in Machine Learning, Explainable AI (XAI) has been offering remarkable performance in interpreting the decisions made by Convolutional Neural Networks (CNNs). To achieve visual explanations for CNNs, methods based on…

In this paper, we propose and analyse two game theoretical models useful to design marketing channels attribution mechanisms based on cooperative TU games and bankruptcy problems, respectively. First, we analyse the Sum Game, a coalitional…

Large language models (LLMs) demonstrate strong capabilities in in-context learning, but verifying the correctness of their generated responses remains a challenge. Prior work has explored attribution at the sentence level, but these…

Not all video frames are equally informative for recognizing an action. It is computationally infeasible to train deep networks on all video frames when actions develop over hundreds of frames. A common heuristic is uniformly sampling a…

This paper addresses the task of segmenting moving objects in unconstrained videos. We introduce a novel two-stream neural network with an explicit memory module to achieve this. The two streams of the network encode spatial and temporal…

Reward design is of great importance for solving complex tasks with reinforcement learning. Recent studies have explored using image-text similarity produced by vision-language models (VLMs) to augment rewards of a task with visual…

In this dissertation, we analyze the computational properties of game-theoretic centrality measures. The key idea behind game-theoretic approach to network analysis is to treat nodes as players in a cooperative game, where the value of each…

Despite the rapid progress of video generation models, the role of data in influencing motion is poorly understood. We present Motive (MOTIon attribution for Video gEneration), a motion-centric, gradient-based data attribution framework…

In this work we propose a simple unsupervised approach for next frame prediction in video. Instead of directly predicting the pixels in a frame given past frames, we predict the transformations needed for generating the next frame in a…

Semantic Segmentation combines two sub-tasks: the identification of pixel-level image masks and the application of semantic labels to those masks. Recently, so-called Foundation Models have been introduced; general models trained on very…

Distributional data Shapley value (DShapley) has recently been proposed as a principled framework to quantify the contribution of individual datum in machine learning. DShapley develops the foundational game theory concept of Shapley values…

Large Language Models (LLMs) are increasingly used in systems that retrieve and summarize content from multiple sources, such as search engines and AI assistants. While these systems enhance user experience through coherent summaries, they…

The burgeoning growth of the esports and multiplayer online gaming community has highlighted the critical importance of evaluating the Most Valuable Player (MVP). The establishment of an explainable and practical MVP evaluation method is…

To date, machine learning for human action recognition in video has been widely implemented in sports activities. Although some studies have been successful in the past, precision is still the most significant concern. In this study, we…

Statistical classification of actions in videos is mostly performed by extracting relevant features, particularly covariance features, from image frames and studying time series associated with temporal evolutions of these features. A…

Explaining AI systems is fundamental both to the development of high performing models and to the trust placed in them by their users. The Shapley framework for explainability has strength in its general applicability combined with its…

Video-based human pose estimation models aim to address scenarios that cannot be effectively solved by static image models such as motion blur, out-of-focus and occlusion. Most existing approaches consist of two stages: detecting human…

The study of neural networks from the perspective of Fourier features has garnered significant attention. While existing analytical research suggests that neural networks tend to learn low-frequency features, a clear attribution method for…

Efficient streaming video generation is critical for simulating interactive and dynamic worlds. Existing methods distill few-step video diffusion models with sliding window attention, using initial frames as sink tokens to maintain…