LLM as A Robotic Brain: Unifying Egocentric Memory and Control

Embodied AI focuses on the study and development of intelligent systems that possess a physical or virtual embodiment (i.e. robots) and are able to dynamically interact with their environment. Memory and control are the two essential parts of an embodied system and usually require separate frameworks to model each of them. In this paper, we propose a novel and generalizable framework called LLM-Brain: using Large-scale Language Model as a robotic brain to unify egocentric memory and control. The LLM-Brain framework integrates multiple multimodal language models for robotic tasks, utilizing a zero-shot learning approach. All components within LLM-Brain communicate using natural language in closed-loop multi-round dialogues that encompass perception, planning, control, and memory. The core of the system is an embodied LLM to maintain egocentric memory and control the robot. We demonstrate LLM-Brain by examining two downstream tasks: active exploration and embodied question answering. The active exploration tasks require the robot to extensively explore an unknown environment within a limited number of actions. Meanwhile, the embodied question answering tasks necessitate that the robot answers questions based on observations acquired during prior explorations.

Large-capacity and Flexible Video Steganography via Invertible Neural Network

Video steganography is the art of unobtrusively concealing secret data in a cover video and then recovering the secret data through a decoding protocol at the receiver end. Although several attempts have been made, most of them are limited to low-capacity and fixed steganography. To rectify these weaknesses, we propose a Large-capacity and Flexible Video Steganography Network (LF-VSN) in this paper. For large-capacity, we present a reversible pipeline to perform multiple videos hiding and recovering through a single invertible neural network (INN). Our method can hide/recover 7 secret videos in/from 1 cover video with promising performance. For flexibility, we propose a key-controllable scheme, enabling different receivers to recover particular secret videos from the same cover video through specific keys. Moreover, we further improve the flexibility by proposing a scalable strategy in multiple videos hiding, which can hide variable numbers of secret videos in a cover video with a single model and a single training session. Extensive experiments demonstrate that with the significant improvement of the video steganography performance, our proposed LF-VSN has high security, large hiding capacity, and flexibility. The source code is available at https://github.com/MC-E/LF-VSN.

Revisiting Test Time Adaptation under Online Evaluation

This paper proposes a novel online evaluation protocol for Test Time Adaptation (TTA) methods, which penalizes slower methods by providing them with fewer samples for adaptation. TTA methods leverage unlabeled data at test time to adapt to distribution shifts. Though many effective methods have been proposed, their impressive performance usually comes at the cost of significantly increased computation budgets. Current evaluation protocols overlook the effect of this extra computation cost, affecting their real-world applicability. To address this issue, we propose a more realistic evaluation protocol for TTA methods, where data is received in an online fashion from a constant-speed data stream, thereby accounting for the method's adaptation speed. We apply our proposed protocol to benchmark several TTA methods on multiple datasets and scenarios. Extensive experiments shows that, when accounting for inference speed, simple and fast approaches can outperform more sophisticated but slower methods. For example, SHOT from 2020 outperforms the state-of-the-art method SAR from 2023 under our online setting. Our online evaluation protocol emphasizes the need for developing TTA methods that are efficient and applicable in realistic settings.

VARS: Video Assistant Referee System for Automated Soccer Decision Making from Multiple Views

The Video Assistant Referee (VAR) has revolutionized association football, enabling referees to review incidents on the pitch, make informed decisions, and ensure fairness. However, due to the lack of referees in many countries and the high cost of the VAR infrastructure, only professional leagues can benefit from it. In this paper, we propose a Video Assistant Referee System (VARS) that can automate soccer decision-making. VARS leverages the latest findings in multi-view video analysis, to provide real-time feedback to the referee, and help them make informed decisions that can impact the outcome of a game. To validate VARS, we introduce SoccerNet-MVFoul, a novel video dataset of soccer fouls from multiple camera views, annotated with extensive foul descriptions by a professional soccer referee, and we benchmark our VARS to automatically recognize the characteristics of these fouls. We believe that VARS has the potential to revolutionize soccer refereeing and take the game to new heights of fairness and accuracy across all levels of professional and amateur federations.

SoccerNet-Caption: Dense Video Captioning for Soccer Broadcasts Commentaries

Soccer is more than just a game - it is a passion that transcends borders and unites people worldwide. From the roar of the crowds to the excitement of the commentators, every moment of a soccer match is a thrill. Yet, with so many games happening simultaneously, fans cannot watch them all live. Notifications for main actions can help, but lack the engagement of live commentary, leaving fans feeling disconnected. To fulfill this need, we propose in this paper a novel task of dense video captioning focusing on the generation of textual commentaries anchored with single timestamps. To support this task, we additionally present a challenging dataset consisting of almost 37k timestamped commentaries across 715.9 hours of soccer broadcast videos. Additionally, we propose a first benchmark and baseline for this task, highlighting the difficulty of temporally anchoring commentaries yet showing the capacity to generate meaningful commentaries. By providing broadcasters with a tool to summarize the content of their video with the same level of engagement as a live game, our method could help satisfy the needs of the numerous fans who follow their team but cannot necessarily watch the live game. We believe our method has the potential to enhance the accessibility and understanding of soccer content for a wider audience, bringing the excitement of the game to more people.

Towards Active Learning for Action Spotting in Association Football Videos

Association football is a complex and dynamic sport, with numerous actions occurring simultaneously in each game. Analyzing football videos is challenging and requires identifying subtle and diverse spatio-temporal patterns. Despite recent advances in computer vision, current algorithms still face significant challenges when learning from limited annotated data, lowering their performance in detecting these patterns. In this paper, we propose an active learning framework that selects the most informative video samples to be annotated next, thus drastically reducing the annotation effort and accelerating the training of action spotting models to reach the highest accuracy at a faster pace. Our approach leverages the notion of uncertainty sampling to select the most challenging video clips to train on next, hastening the learning process of the algorithm. We demonstrate that our proposed active learning framework effectively reduces the required training data for accurate action spotting in football videos. We achieve similar performances for action spotting with NetVLAD++ on SoccerNet-v2, using only one-third of the dataset, indicating significant capabilities for reducing annotation time and improving data efficiency. We further validate our approach on two new datasets that focus on temporally localizing actions of headers and passes, proving its effectiveness across different action semantics in football. We believe our active learning framework for action spotting would support further applications of action spotting algorithms and accelerate annotation campaigns in the sports domain.

Improving Visual Question Answering Models through Robustness Analysis and In-Context Learning with a Chain of Basic Questions

Deep neural networks have been critical in the task of Visual Question Answering (VQA), with research traditionally focused on improving model accuracy. Recently, however, there has been a trend towards evaluating the robustness of these models against adversarial attacks. This involves assessing the accuracy of VQA models under increasing levels of noise in the input, which can target either the image or the proposed query question, dubbed the main question. However, there is currently a lack of proper analysis of this aspect of VQA. This work proposes a new method that utilizes semantically related questions, referred to as basic questions, acting as noise to evaluate the robustness of VQA models. It is hypothesized that as the similarity of a basic question to the main question decreases, the level of noise increases. To generate a reasonable noise level for a given main question, a pool of basic questions is ranked based on their similarity to the main question, and this ranking problem is cast as a LASSO optimization problem. Additionally, this work proposes a novel robustness measure, R_score, and two basic question datasets to standardize the analysis of VQA model robustness. The experimental results demonstrate that the proposed evaluation method effectively analyzes the robustness of VQA models. Moreover, the experiments show that in-context learning with a chain of basic questions can enhance model accuracy.

Boundary-Denoising for Video Activity Localization

Video activity localization aims at understanding the semantic content in long untrimmed videos and retrieving actions of interest. The retrieved action with its start and end locations can be used for highlight generation, temporal action detection, etc. Unfortunately, learning the exact boundary location of activities is highly challenging because temporal activities are continuous in time, and there are often no clear-cut transitions between actions. Moreover, the definition of the start and end of events is subjective, which may confuse the model. To alleviate the boundary ambiguity, we propose to study the video activity localization problem from a denoising perspective. Specifically, we propose an encoder-decoder model named DenoiseLoc. During training, a set of action spans is randomly generated from the ground truth with a controlled noise scale. Then we attempt to reverse this process by boundary denoising, allowing the localizer to predict activities with precise boundaries and resulting in faster convergence speed. Experiments show that DenoiseLoc advances %in several video activity understanding tasks. For example, we observe a gain of +12.36% average mAP on QV-Highlights dataset and +1.64% mAP@0.5 on THUMOS'14 dataset over the baseline. Moreover, DenoiseLoc achieves state-of-the-art performance on TACoS and MAD datasets, but with much fewer predictions compared to other current methods.