Related papers: Perceive What Matters: Relevance-Driven Scheduling…
How humans and machines make sense of current inputs for relation reasoning and question-answering while putting the perceived information into context of our past memories, has been a challenging conundrum in cognitive science and…
General scene perception has progressed from object recognition toward open-vocabulary grounding, part localization, and affordance prediction. Yet these capabilities are often realized as isolated predictions that localize objects, parts,…
Humans perceive the world by concurrently processing and fusing high-dimensional inputs from multiple modalities such as vision and audio. Machine perception models, in stark contrast, are typically modality-specific and optimised for…
Active perception in vision-based robotic manipulation aims to move the camera toward more informative observation viewpoints, thereby providing high-quality perceptual inputs for downstream tasks. Most existing active perception methods…
Autonomous driving requires the model to perceive the environment and (re)act within a low latency for safety. While past works ignore the inevitable changes in the environment after processing, streaming perception is proposed to jointly…
The increasing adoption of human-robot interaction presents opportunities for technology to positively impact lives, particularly those with visual impairments, through applications such as guide-dog-like assistive robotics. We present a…
Most cognitive architectures rely on discrete representation, both in space (e.g., objects) and in time (e.g., events). However, a robot interaction with the world is inherently continuous, both in space and in time. The segmentation of the…
Transformer architectures are now central to sequence modeling tasks. At its heart is the attention mechanism, which enables effective modeling of long-term dependencies in a sequence. Recently, transformers have been successfully applied…
Multi-agent collaborative perception (MCP) has recently attracted much attention. It includes three key processes: communication for sharing, collaboration for integration, and reconstruction for different downstream tasks. Existing methods…
Real-time perception requires planned resource utilization. Computational planning in real-time perception is governed by two considerations -- accuracy and latency. There exist run-time decisions (e.g. choice of input resolution) that…
In robotics, Vision-Language-Action (VLA) models that integrate diverse multimodal signals from multi-view inputs have emerged as an effective approach. However, most prior work adopts static fusion that processes all visual inputs…
Recently, several studies have shown that utilizing contextual information to perceive target states is crucial for object tracking. They typically capture context by incorporating multiple video frames. However, these naive frame-context…
We present Prompt Cache, an approach for accelerating inference for large language models (LLM) by reusing attention states across different LLM prompts. Many input prompts have overlapping text segments, such as system messages, prompt…
Scene understanding is one of the core tasks in computer vision, aiming to extract semantic information from images to identify objects, scene categories, and their interrelationships. Although advancements in Vision-Language Models (VLMs)…
Understanding mid-level road semantics, which capture the structural and contextual cues that link low-level perception to high-level planning, is essential for reliable autonomous driving and digital map construction. However, existing…
Perception serves as a critical component in the functionality of autonomous agents. However, the intricate relationship between perception metrics and robotic metrics remains unclear, leading to ambiguity in the development and fine-tuning…
Video summarization intends to produce a concise video summary by effectively capturing and combining the most informative parts of the whole content. Existing approaches for video summarization regard the task as a frame-wise keyframe…
Real-time video surveillance has become a crucial technology for smart cities, made possible through the large-scale deployment of mobile and fixed video cameras. In this paper, we propose situation-aware streaming, for real-time…
Given a question-image input, the Visual Commonsense Reasoning (VCR) model can predict an answer with the corresponding rationale, which requires inference ability from the real world. The VCR task, which calls for exploiting the…
Collaborative multi-robot perception provides multiple views of an environment, offering varying perspectives to collaboratively understand the environment even when individual robots have poor points of view or when occlusions are caused…