StoryVideoQA: Scaling Deep Video Understanding with a Large-Scale, Multi-Genre and Auto-Generated Dataset

Video question answering (VideoQA) aims to answer questions about given videos. While existing approaches excel on factoid VideoQA, they struggle with deep video understanding (DVU), which requires the comprehension of complex storylines. This challenge arises from the inherent long-range video content, multi-faceted question types, and instance-level story elements, all of which constrain the scale and diversity of manually constructed DVU datasets. These difficulties constrain the scale and diversity of manually-constructed DVU dataset. To address these, we previously introduced StoryMind to automatically construct DVU datasets with balanced fine-grained topics. Though it can generate high-quality question-answer pairs (QAs) for TV series, it suffers significant performance degradation when handling longer and more complex movies. In this paper, we further design StoryMindv2, an enhanced multi-agent collaboration framework to generate high-quality DVU datasets for both TV series and movies. By integrating a novel supervisor-guided generation mechanism and a refined multi-reviewer voting strategy, the framework is utilized to construct StoryVideoQA, the largest DVU dataset to date, featuring over 363K QAs on 393.2 hours diverse story videos including TV series (avg. 1,635 seconds) and movies (avg. 7,878 seconds). Comprehensive evaluations of 20 state-of-the-art VideoQA methods on this large-scale benchmark reveal that they cannot fully maintain long-range character associations or construct a coherent understanding of complex storylines. To bridge this gap, we propose PlotTree, a novel video understanding agent, re-organizing long-range video content into a hierarchical plot structure, enabling efficient storyline reasoning on StoryVideoQA. Project page: https://github.com/nercms-mmap/StoryVideoQA/

Deep Reinforcement Learning-based Multi-objective Path Planning on the Off-road Terrain Environment for Ground Vehicles

Due to the energy-consumption efficiency between up-slope and down-slope is hugely different, a path with the shortest length on a complex off-road terrain environment (2.5D map) is not always the path with the least energy consumption. For any energy-sensitive vehicles, realizing a good trade-off between distance and energy consumption on 2.5D path planning is significantly meaningful. In this paper, a deep reinforcement learning-based 2.5D multi-objective path planning method (DMOP) is proposed. The DMOP can efficiently find the desired path with three steps: (1) Transform the high-resolution 2.5D map into a small-size map. (2) Use a trained deep Q network (DQN) to find the desired path on the small-size map. (3) Build the planned path to the original high-resolution map using a path enhanced method. In addition, the imitation learning method and reward shaping theory are applied to train the DQN. The reward function is constructed with the information of terrain, distance, border. Simulation shows that the proposed method can finish the multi-objective 2.5D path planning task. Also, simulation proves that the method has powerful reasoning capability that enables it to perform arbitrary untrained planning tasks on the same map.