相关论文: ST-Booster: An Iterative SpatioTemporal Perception…

Vision and voice are two vital keys for agents' interaction and learning. In this paper, we present a novel indoor navigation model called Memory Vision-Voice Indoor Navigation (MVV-IN), which receives voice commands and analyzes multimodal…

Vision-and-language navigation (VLN), a frontier study aiming to pave the way for general-purpose robots, has been a hot topic in the computer vision and natural language processing community. The VLN task requires an agent to navigate to a…

Frame quality deterioration is one of the main challenges in the field of video understanding. To compensate for the information loss caused by deteriorated frames, recent approaches exploit transformer-based integration modules to obtain…

Recent advances in Vision-and-Language Navigation in Continuous Environments (VLN-CE) have leveraged multimodal large language models (MLLMs) to achieve zero-shot navigation. However, existing methods often rely on panoramic observations…

In this technical report, we introduce our solution to human-centric spatio-temporal video grounding task. We propose a concise and effective framework named STVGFormer, which models spatiotemporal visual-linguistic dependencies with a…

Current multimodal LLMs encode images as static visual prefixes and rely on text-based reasoning, lacking goal-driven and adaptive visual access. Inspired by human visual perception-where attention is selectively and sequentially shifted…

Vision-Language Models (VLMs) have shown promising capabilities in handling various multimodal tasks, yet they struggle in long-context scenarios, particularly in tasks involving videos, high-resolution images, or lengthy image-text…

Deep neural networks, especially transformer-based architectures, have achieved remarkable success in semantic segmentation for environmental perception. However, existing models process video frames independently, thus failing to leverage…

Human mobility traces, often recorded as sequences of check-ins, provide a unique window into both short-term visiting patterns and persistent lifestyle regularities. In this work we introduce GSTM-HMU, a generative spatio-temporal…

Consecutive frames in a video contain redundancy, but they may also contain relevant complementary information for the detection task. The objective of our work is to leverage this complementary information to improve detection. Therefore,…

In Vision-and-Language Navigation (VLN), researchers typically take an image encoder pre-trained on ImageNet without fine-tuning on the environments that the agent will be trained or tested on. However, the distribution shift between the…

Vision-and-Language Navigation (VLN) requires an agent to follow natural-language instructions, explore the given environments, and reach the desired target locations. These step-by-step navigational instructions are crucial when the agent…

Vision-Language Navigation (VLN) approaches have currently followed two primary paradigms: the end-to-end Vision-Language Model (VLM) policy fine-tuned on navigation trajectories to directly predict actions, and the zero-shot modular…

The alignment of vision-language representations endows current Vision-Language Models (VLMs) with strong multi-modal reasoning capabilities. However, the interpretability of the alignment component remains uninvestigated due to the…

We explore the task of language-guided video segmentation (LVS). Previous algorithms mostly adopt 3D CNNs to learn video representation, struggling to capture long-term context and easily suffering from visual-linguistic misalignment. In…

While pre-training large-scale video-language models (VLMs) has shown remarkable potential for various downstream video-language tasks, existing VLMs can still suffer from certain commonly seen limitations, e.g., coarse-grained cross-modal…

In Vision-and-Language Navigation (VLN), an agent is required to plan a path to the target specified by the language instruction, using its visual observations. Consequently, prevailing VLN methods primarily focus on building powerful…

Despite significant recent progress of Multimodal Large Language Models (MLLMs), current MLLMs are challenged by "spatio-temporal" prompts, i.e., prompts that refer to 1) the entirety of an environment encoded in a point cloud that the MLLM…

Interaction and navigation defined by natural language instructions in dynamic environments pose significant challenges for neural agents. This paper focuses on addressing two challenges: handling long sequence of subtasks, and…

Spatial reasoning -- the ability to perceive and reason about relationships in space -- advances vision-language models (VLMs) from visual perception toward spatial semantic understanding. Existing approaches either revisit local image…