Image Classification and Video Action Recognition are perhaps the two most foundational tasks in computer vision. Consequently, explaining the inner workings of trained deep neural networks is of prime importance. While numerous efforts focus on explaining the decisions of trained deep neural networks in image classification, exploration in the domain of its temporal version, video action recognition, has been scant. In this work, we take a deeper look at this problem. We begin by revisiting Grad-CAM, one of the popular feature attribution methods for Image Classification, and its extension to Video Action Recognition tasks and examine the method's limitations. To address these, we introduce Video-TCAV, by building on TCAV for Image Classification tasks, which aims to quantify the importance of specific concepts in the decision-making process of Video Action Recognition models. As the scalable generation of concepts is still an open problem, we propose a machine-assisted approach to generate spatial and spatiotemporal concepts relevant to Video Action Recognition for testing Video-TCAV. We then establish the importance of temporally-varying concepts by demonstrating the superiority of dynamic spatiotemporal concepts over trivial spatial concepts. In conclusion, we introduce a framework for investigating hypotheses in action recognition and quantitatively testing them, thus advancing research in the explainability of deep neural networks used in video action recognition.

Visual Programming (VP) has emerged as a powerful framework for Visual Question Answering (VQA). By generating and executing bespoke code for each question, these methods demonstrate impressive compositional and reasoning capabilities, especially in few-shot and zero-shot scenarios. However, existing VP methods generate all code in a single function, resulting in code that is suboptimal in terms of both accuracy and interpretability. Inspired by human coding practices, we propose Recursive Visual Programming (RVP), which simplifies generated routines, provides more efficient problem solving, and can manage more complex data structures. RVP is inspired by human coding practices and approaches VQA tasks with an iterative recursive code generation approach, allowing decomposition of complicated problems into smaller parts. Notably, RVP is capable of dynamic type assignment, i.e., as the system recursively generates a new piece of code, it autonomously determines the appropriate return type and crafts the requisite code to generate that output. We show RVP's efficacy through extensive experiments on benchmarks including VSR, COVR, GQA, and NextQA, underscoring the value of adopting human-like recursive and modular programming techniques for solving VQA tasks through coding.

Machine learning (ML) models that achieve high average accuracy can still underperform on semantically coherent subsets (i.e. "slices") of data. This behavior can have significant societal consequences for the safety or bias of the model in deployment, but identifying these underperforming slices can be difficult in practice, especially in domains where practitioners lack access to group annotations to define coherent subsets of their data. Motivated by these challenges, ML researchers have developed new slice discovery algorithms that aim to group together coherent and high-error subsets of data. However, there has been little evaluation focused on whether these tools help humans form correct hypotheses about where (for which groups) their model underperforms. We conduct a controlled user study (N = 15) where we show 40 slices output by two state-of-the-art slice discovery algorithms to users, and ask them to form hypotheses about where an object detection model underperforms. Our results provide positive evidence that these tools provide some benefit over a naive baseline, and also shed light on challenges faced by users during the hypothesis formation step. We conclude by discussing design opportunities for ML and HCI researchers. Our findings point to the importance of centering users when designing and evaluating new tools for slice discovery.

In recent years, the field of computer vision has seen significant advancements thanks to the development of large language models (LLMs). These models have enabled more effective and sophisticated interactions between humans and machines, paving the way for novel techniques that blur the lines between human and machine intelligence. In this paper, we introduce a new paradigm for object detection that we call reasoning-based object detection. Unlike conventional object detection methods that rely on specific object names, our approach enables users to interact with the system using natural language instructions, allowing for a higher level of interactivity. Our proposed method, called DetGPT, leverages state-of-the-art multi-modal models and open-vocabulary object detectors to perform reasoning within the context of the user's instructions and the visual scene. This enables DetGPT to automatically locate the object of interest based on the user's expressed desires, even if the object is not explicitly mentioned. For instance, if a user expresses a desire for a cold beverage, DetGPT can analyze the image, identify a fridge, and use its knowledge of typical fridge contents to locate the beverage. This flexibility makes our system applicable across a wide range of fields, from robotics and automation to autonomous driving. Overall, our proposed paradigm and DetGPT demonstrate the potential for more sophisticated and intuitive interactions between humans and machines. We hope that our proposed paradigm and approach will provide inspiration to the community and open the door to more interative and versatile object detection systems. Our project page is launched at detgpt.github.io.

The tennis racket has a very ancient origin. In fact it was used by the ancient Romans. It was then mainly used for the tennis court. The tennis racket, similar to that of the shuttlecock and basketball string, is characterized by a handle of different sizes, by a stem, by a central part, called the heart that joins the stem to the plate, therefore by the wider and rounded part constituted by the stringing, called the plate of the strings. The shape and materials used have slowly evolved over time, guaranteeing an improvement in impact and ball control, which was previously more difficult. Built in different materials, originally it was in wood, then it slowly evolved up to our days first to steel, then to aluminum alloys to get to carbon and graphite, the two materials now most used.

Image classifiers often use spurious patterns, such as "relying on the presence of a person to detect a tennis racket, which do not generalize. In this work, we present an end-to-end pipeline for identifying and mitigating spurious patterns for such models, under the assumption that we have access to pixel-wise object-annotations. We start by identifying patterns such as "the model's prediction for tennis racket changes 63% of the time if we hide the people." Then, if a pattern is spurious, we mitigate it via a novel form of data augmentation. We demonstrate that our method identifies a diverse set of spurious patterns and that it mitigates them by producing a model that is both more accurate on a distribution where the spurious pattern is not helpful and more robust to distribution shift.