MASH-VLM: Mitigating Action-Scene Hallucination in Video-LLMs through Disentangled Spatial-Temporal Representations

In this work, we tackle action-scene hallucination in Video Large Language Models (Video-LLMs), where models incorrectly predict actions based on the scene context or scenes based on observed actions. We observe that existing Video-LLMs often suffer from action-scene hallucination due to two main factors. First, existing Video-LLMs intermingle spatial and temporal features by applying an attention operation across all tokens. Second, they use the standard Rotary Position Embedding (RoPE), which causes the text tokens to overemphasize certain types of tokens depending on their sequential orders. To address these issues, we introduce MASH-VLM, Mitigating Action-Scene Hallucination in Video-LLMs through disentangled spatial-temporal representations. Our approach includes two key innovations: (1) DST-attention, a novel attention mechanism that disentangles the spatial and temporal tokens within the LLM by using masked attention to restrict direct interactions between the spatial and temporal tokens; (2) Harmonic-RoPE, which extends the dimensionality of the positional IDs, allowing the spatial and temporal tokens to maintain balanced positions relative to the text tokens. To evaluate the action-scene hallucination in Video-LLMs, we introduce the UNSCENE benchmark with 1,320 videos and 4,078 QA pairs. Extensive experiments demonstrate that MASH-VLM achieves state-of-the-art results on the UNSCENE benchmark, as well as on existing video understanding benchmarks.

The Geometry of Optimal Gait Families for Steering Kinematic Locomoting Systems

Motion planning for locomotion systems typically requires translating high-level rigid-body tasks into low-level joint trajectories-a process that is straightforward for car-like robots with fixed, unbounded actuation inputs but more challenging for systems like snake robots, where the mapping depends on the current configuration and is constrained by joint limits. In this paper, we focus on generating continuous families of optimal gaits-collections of gaits parameterized by step size or steering rate-to enhance controllability and maneuverability. We uncover the underlying geometric structure of these optimal gait families and propose methods for constructing them using both global and local search strategies, where the local method and the global method compensate each other. The global search approach is robust to nonsmooth behavior, albeit yielding reduced-order solutions, while the local search provides higher accuracy but can be unstable near nonsmooth regions. To demonstrate our framework, we generate optimal gait families for viscous and perfect-fluid three-link swimmers. This work lays a foundation for integrating low-level joint controllers with higher-level motion planners in complex locomotion systems.

HiCM$^2$: Hierarchical Compact Memory Modeling for Dense Video Captioning

With the growing demand for solutions to real-world video challenges, interest in dense video captioning (DVC) has been on the rise. DVC involves the automatic captioning and localization of untrimmed videos. Several studies highlight the challenges of DVC and introduce improved methods utilizing prior knowledge, such as pre-training and external memory. In this research, we propose a model that leverages the prior knowledge of human-oriented hierarchical compact memory inspired by human memory hierarchy and cognition. To mimic human-like memory recall, we construct a hierarchical memory and a hierarchical memory reading module. We build an efficient hierarchical compact memory by employing clustering of memory events and summarization using large language models. Comparative experiments demonstrate that this hierarchical memory recall process improves the performance of DVC by achieving state-of-the-art performance on YouCook2 and ViTT datasets.

Geometric Optimal Control of Mechanical Systems with Gravitational and Resistive Force

Optimal control plays a crucial role in numerous mechanical and robotic applications. Broadly, optimal control methods are divided into direct methods (which optimize trajectories directly via discretization) and indirect methods (which transform optimality conditions into equations that guarantee optimal trajectories). While direct methods could mask geometric insights into system dynamics due to discretization, indirect methods offer a deeper understanding of the system's geometry. In this paper, we propose a geometric framework for understanding optimal control in mechanical systems, focusing on the combined effects of inertia, drag, and gravitational forces. By modeling mechanical systems as configuration manifolds equipped with kinetic and drag metrics, alongside a potential field, we explore how these factors influence trajectory optimization. We derive optimal control equations incorporating these effects and apply them to two-link and UR5 robotic manipulators, demonstrating how manifold curvature and resistive forces shape optimal trajectories. This work offers a comprehensive geometric approach to optimal control, with broad applications to robotic systems.

PCEvE: Part Contribution Evaluation Based Model Explanation for Human Figure Drawing Assessment and Beyond

For automatic human figure drawing (HFD) assessment tasks, such as diagnosing autism spectrum disorder (ASD) using HFD images, the clarity and explainability of a model decision are crucial. Existing pixel-level attribution-based explainable AI (XAI) approaches demand considerable effort from users to interpret the semantic information of a region in an image, which can be often time-consuming and impractical. To overcome this challenge, we propose a part contribution evaluation based model explanation (PCEvE) framework. On top of the part detection, we measure the Shapley Value of each individual part to evaluate the contribution to a model decision. Unlike existing attribution-based XAI approaches, the PCEvE provides a straightforward explanation of a model decision, i.e., a part contribution histogram. Furthermore, the PCEvE expands the scope of explanations beyond the conventional sample-level to include class-level and task-level insights, offering a richer, more comprehensive understanding of model behavior. We rigorously validate the PCEvE via extensive experiments on multiple HFD assessment datasets. Also, we sanity-check the proposed method with a set of controlled experiments. Additionally, we demonstrate the versatility and applicability of our method to other domains by applying it to a photo-realistic dataset, the Stanford Cars.

Optimal Control Approach for Gait Transition with Riemannian Splines

Robotic locomotion often relies on sequenced gaits to efficiently convert control input into desired motion. Despite extensive studies on gait optimization, achieving smooth and efficient gait transitions remains challenging. In this paper, we propose a general solver based on geometric optimal control methods, leveraging insights from previous works on gait efficiency. Building upon our previous work, we express the effort to execute the trajectory as distinct geometric objects, transforming the optimization problems into boundary value problems. To validate our approach, we generate gait transition trajectories for three-link swimmers across various fluid environments. This work provides insights into optimal trajectory geometries and mechanical considerations for robotic locomotion.

Infusing Environmental Captions for Long-Form Video Language Grounding

In this work, we tackle the problem of long-form video-language grounding (VLG). Given a long-form video and a natural language query, a model should temporally localize the precise moment that answers the query. Humans can easily solve VLG tasks, even with arbitrarily long videos, by discarding irrelevant moments using extensive and robust knowledge gained from experience. Unlike humans, existing VLG methods are prone to fall into superficial cues learned from small-scale datasets, even when they are within irrelevant frames. To overcome this challenge, we propose EI-VLG, a VLG method that leverages richer textual information provided by a Multi-modal Large Language Model (MLLM) as a proxy for human experiences, helping to effectively exclude irrelevant frames. We validate the effectiveness of the proposed method via extensive experiments on a challenging EgoNLQ benchmark.

Open-Set Domain Adaptation for Semantic Segmentation

Unsupervised domain adaptation (UDA) for semantic segmentation aims to transfer the pixel-wise knowledge from the labeled source domain to the unlabeled target domain. However, current UDA methods typically assume a shared label space between source and target, limiting their applicability in real-world scenarios where novel categories may emerge in the target domain. In this paper, we introduce Open-Set Domain Adaptation for Semantic Segmentation (OSDA-SS) for the first time, where the target domain includes unknown classes. We identify two major problems in the OSDA-SS scenario as follows: 1) the existing UDA methods struggle to predict the exact boundary of the unknown classes, and 2) they fail to accurately predict the shape of the unknown classes. To address these issues, we propose Boundary and Unknown Shape-Aware open-set domain adaptation, coined BUS. Our BUS can accurately discern the boundaries between known and unknown classes in a contrastive manner using a novel dilation-erosion-based contrastive loss. In addition, we propose OpenReMix, a new domain mixing augmentation method that guides our model to effectively learn domain and size-invariant features for improving the shape detection of the known and unknown classes. Through extensive experiments, we demonstrate that our proposed BUS effectively detects unknown classes in the challenging OSDA-SS scenario compared to the previous methods by a large margin. The code is available at https://github.com/KHU-AGI/BUS.

Do You Remember? Dense Video Captioning with Cross-Modal Memory Retrieval

There has been significant attention to the research on dense video captioning, which aims to automatically localize and caption all events within untrimmed video. Several studies introduce methods by designing dense video captioning as a multitasking problem of event localization and event captioning to consider inter-task relations. However, addressing both tasks using only visual input is challenging due to the lack of semantic content. In this study, we address this by proposing a novel framework inspired by the cognitive information processing of humans. Our model utilizes external memory to incorporate prior knowledge. The memory retrieval method is proposed with cross-modal video-to-text matching. To effectively incorporate retrieved text features, the versatile encoder and the decoder with visual and textual cross-attention modules are designed. Comparative experiments have been conducted to show the effectiveness of the proposed method on ActivityNet Captions and YouCook2 datasets. Experimental results show promising performance of our model without extensive pretraining from a large video dataset.

MobileSAMv2: Faster Segment Anything to Everything

Segment anything model (SAM) addresses two practical yet challenging segmentation tasks: \textbf{segment anything (SegAny)}, which utilizes a certain point to predict the mask for a single object of interest, and \textbf{segment everything (SegEvery)}, which predicts the masks for all objects on the image. What makes SegAny slow for SAM is its heavyweight image encoder, which has been addressed by MobileSAM via decoupled knowledge distillation. The efficiency bottleneck of SegEvery with SAM, however, lies in its mask decoder because it needs to first generate numerous masks with redundant grid-search prompts and then perform filtering to obtain the final valid masks. We propose to improve its efficiency by directly generating the final masks with only valid prompts, which can be obtained through object discovery. Our proposed approach not only helps reduce the total time on the mask decoder by at least 16 times but also achieves superior performance. Specifically, our approach yields an average performance boost of 3.6\% (42.5\% \textit{v.s.} 38.9\%) for zero-shot object proposal on the LVIS dataset with the mask AR@$K$ metric. Qualitative results show that our approach generates fine-grained masks while avoiding over-segmenting things. This project targeting faster SegEvery than the original SAM is termed MobileSAMv2 to differentiate from MobileSAM which targets faster SegAny. Moreover, we demonstrate that our new prompt sampling is also compatible with the distilled image encoders in MobileSAM, contributing to a unified framework for efficient SegAny and SegEvery. The code is available at the same link as MobileSAM Project \href{https://github.com/ChaoningZhang/MobileSAM}{\textcolor{red}{https://github.com/ChaoningZhang/MobileSAM}}. \end{abstract}