VideoLLM-online: Online Video Large Language Model for Streaming Video

Recent Large Language Models have been enhanced with vision capabilities, enabling them to comprehend images, videos, and interleaved vision-language content. However, the learning methods of these large multimodal models typically treat videos as predetermined clips, making them less effective and efficient at handling streaming video inputs. In this paper, we propose a novel Learning-In-Video-Stream (LIVE) framework, which enables temporally aligned, long-context, and real-time conversation within a continuous video stream. Our LIVE framework comprises comprehensive approaches to achieve video streaming dialogue, encompassing: (1) a training objective designed to perform language modeling for continuous streaming inputs, (2) a data generation scheme that converts offline temporal annotations into a streaming dialogue format, and (3) an optimized inference pipeline to speed up the model responses in real-world video streams. With our LIVE framework, we built VideoLLM-online model upon Llama-2/Llama-3 and demonstrate its significant advantages in processing streaming videos. For instance, on average, our model can support streaming dialogue in a 5-minute video clip at over 10 FPS on an A100 GPU. Moreover, it also showcases state-of-the-art performance on public offline video benchmarks, such as recognition, captioning, and forecasting. The code, model, data, and demo have been made available at https://showlab.github.io/videollm-online.

ASSISTGUI: Task-Oriented Desktop Graphical User Interface Automation

Graphical User Interface (GUI) automation holds significant promise for assisting users with complex tasks, thereby boosting human productivity. Existing works leveraging Large Language Model (LLM) or LLM-based AI agents have shown capabilities in automating tasks on Android and Web platforms. However, these tasks are primarily aimed at simple device usage and entertainment operations. This paper presents a novel benchmark, AssistGUI, to evaluate whether models are capable of manipulating the mouse and keyboard on the Windows platform in response to user-requested tasks. We carefully collected a set of 100 tasks from nine widely-used software applications, such as, After Effects and MS Word, each accompanied by the necessary project files for better evaluation. Moreover, we propose an advanced Actor-Critic Embodied Agent framework, which incorporates a sophisticated GUI parser driven by an LLM-agent and an enhanced reasoning mechanism adept at handling lengthy procedural tasks. Our experimental results reveal that our GUI Parser and Reasoning mechanism outshine existing methods in performance. Nevertheless, the potential remains substantial, with the best model attaining only a 46% success rate on our benchmark. We conclude with a thorough analysis of the current methods' limitations, setting the stage for future breakthroughs in this domain.

AssistQ: Affordance-centric Question-driven Task Completion for Egocentric Assistant

A long-standing goal of intelligent assistants such as AR glasses/robots has been to assist users in affordance-centric real-world scenarios, such as "how can I run the microwave for 1 minute?". However, there is still no clear task definition and suitable benchmarks. In this paper, we define a new task called Affordance-centric Question-driven Task Completion, where the AI assistant should learn from instructional videos and scripts to guide the user step-by-step. To support the task, we constructed AssistQ, a new dataset comprising 529 question-answer samples derived from 100 newly filmed first-person videos. Each question should be completed with multi-step guidances by inferring from visual details (e.g., buttons' position) and textural details (e.g., actions like press/turn). To address this unique task, we developed a Question-to-Actions (Q2A) model that significantly outperforms several baseline methods while still having large room for improvement. We expect our task and dataset to advance Egocentric AI Assistant's development. Our project page is available at: https://showlab.github.io/assistq

AssistSR: Affordance-centric Question-driven Video Segment Retrieval

It is still a pipe dream that AI assistants on phone and AR glasses can assist our daily life in addressing our questions like "how to adjust the date for this watch?" and "how to set its heating duration? (while pointing at an oven)". The queries used in conventional tasks (i.e. Video Question Answering, Video Retrieval, Moment Localization) are often factoid and based on pure text. In contrast, we present a new task called Affordance-centric Question-driven Video Segment Retrieval (AQVSR). Each of our questions is an image-box-text query that focuses on affordance of items in our daily life and expects relevant answer segments to be retrieved from a corpus of instructional video-transcript segments. To support the study of this AQVSR task, we construct a new dataset called AssistSR. We design novel guidelines to create high-quality samples. This dataset contains 1.4k multimodal questions on 1k video segments from instructional videos on diverse daily-used items. To address AQVSR, we develop a straightforward yet effective model called Dual Multimodal Encoders (DME) that significantly outperforms several baseline methods while still having large room for improvement in the future. Moreover, we present detailed ablation analyses. Our codes and data are available at https://github.com/StanLei52/AQVSR.