Related papers: ExACT: Language-guided Conceptual Reasoning and Un…
This work aims at advancing temporal action detection (TAD) using an encoder-decoder framework with action queries, similar to DETR, which has shown great success in object detection. However, the framework suffers from several problems if…
Autonomous driving (AD) systems relying solely on onboard sensors may fail to detect distant or obstacle hazards, potentially causing preventable collisions; however, existing transformer-based Vehicle-to-Everything (V2X) approaches, which…
Event cameras provide microsecond-level temporal resolution, low latency, and high dynamic range, offering potential for perception under fast motion and challenging illumination conditions. However, existing Event-based Object Detection…
Event Detection, which aims to identify and classify mentions of event instances from unstructured articles, is an important task in Natural Language Processing (NLP). Existing techniques for event detection only use homogeneous one-hot…
Ensuring the safety of all traffic participants is a prerequisite for bringing intelligent vehicles closer to practical applications. The assistance system should not only achieve high accuracy under normal conditions, but obtain robust…
Adaptive sampling that exploits the spatiotemporal redundancy in videos is critical for always-on action recognition on wearable devices with limited computing and battery resources. The commonly used fixed sampling strategy is not…
Conditional human animation traditionally animates static reference images using pose-based motion cues extracted from video data. However, these video-derived cues often suffer from low temporal resolution, motion blur, and unreliable…
With the advent of deep learning, text generation language models have improved dramatically, with text at a similar level as human-written text. This can lead to rampant misinformation because content can now be created cheaply and…
Different from universal object detection, referring expression comprehension (REC) aims to locate specific objects referred to by natural language expressions. The expression provides high-level concepts of relevant visual and contextual…
Entity-level sentiment classification involves identifying the sentiment polarity linked to specific entities within text. This task poses several challenges: effectively modeling the subtle and complex interactions between entities and…
Omnimodal large language models have made significant strides in unifying audio and visual modalities; however, they often face challenges in fine-grained cross-modal understanding and have difficulty with multimodal alignment. To address…
While large language models (LLMs) have demonstrated impressive capabilities across tasks in language understanding and interactive decision making, their abilities for reasoning (e.g. chain-of-thought prompting) and acting (e.g. action…
Cross-document Event Coreference Resolution (CD-ECR) is a fundamental task in natural language processing (NLP) that seeks to determine whether event mentions across multiple documents refer to the same real-world occurrence. However,…
In recent years, there has been an increased need for the use of active systems - systems required to act automatically based on events, or changes in the environment. Such systems span many areas, from active databases to applications that…
Large Language Models (LLMs) have demonstrated remarkable capabilities in interactive decision-making tasks, but existing methods often struggle with error accumulation and lack robust self-correction mechanisms. We introduce "Reflect…
With the increasing demands on e-commerce platforms, numerous user action history is emerging. Those enriched action records are vital to understand users' interests and intents. Recently, prior works for user behavior prediction mainly…
Effectiveness and interpretability are two essential properties for trustworthy AI systems. Most recent studies in visual reasoning are dedicated to improving the accuracy of predicted answers, and less attention is paid to explaining the…
We introduce a generic visual descriptor, termed as distribution aware retinal transform (DART), that encodes the structural context using log-polar grids for event cameras. The DART descriptor is applied to four different problems, namely…
The event camera is a novel bio-inspired vision sensor. When the brightness change exceeds the preset threshold, the sensor generates events asynchronously. The number of valid events directly affects the performance of event-based tasks,…
Reasoning-acting frameworks enhance large language models (LLMs) by interleaving reasoning with actions for dynamic information acquisition. However, extending this paradigm to graph learning remains underexplored. Graph data is inherently…