中文
相关论文

相关论文: In Defense of Structural Symbolic Representation f…

200 篇论文

Event-Level Video Question Answering (EVQA) requires complex reasoning across video events to obtain the visual information needed to provide optimal answers. However, despite significant progress in model performance, few studies have…

计算机视觉与模式识别 · 计算机科学 2023-05-16 Chenyang Lyu , Tianbo Ji , Yvette Graham , Jennifer Foster

Neuro-symbolic representations have proved effective in learning structure information in vision and language. In this paper, we propose a new model architecture for learning multi-modal neuro-symbolic representations for video captioning.…

计算机视觉与模式识别 · 计算机科学 2020-11-20 Hassan Akbari , Hamid Palangi , Jianwei Yang , Sudha Rao , Asli Celikyilmaz , Roland Fernandez , Paul Smolensky , Jianfeng Gao , Shih-Fu Chang

Video question answering (Video QA) presents a powerful testbed for human-like intelligent behaviors. The task demands new capabilities to integrate video processing, language understanding, binding abstract linguistic concepts to concrete…

计算机视觉与模式识别 · 计算机科学 2021-07-12 Long Hoang Dang , Thao Minh Le , Vuong Le , Truyen Tran

Despite impressive advancements in Visual-Language Models (VLMs) for multi-modal tasks, their reliance on RGB inputs limits precise spatial understanding. Existing methods for integrating spatial cues, such as point clouds or depth, either…

计算机视觉与模式识别 · 计算机科学 2025-10-27 Yang Liu , Ming Ma , Xiaomin Yu , Pengxiang Ding , Han Zhao , Mingyang Sun , Siteng Huang , Donglin Wang

Human understanding of video dynamics relies on forming structured representations of entities, actions, and temporal relations before engaging in abstract reasoning. In contrast, existing Video-LLMs apply unstructured chain-of-thought…

计算与语言 · 计算机科学 2026-05-08 Zinuo Li , Yongxin Guo , Jun Liu , Jiawei Zhan , Xi Jiang , Chengjie Wang , Mohammed Bennamoun , Farid Boussaid , Feng Zheng , Qiuhong Ke

Semantic role theory is a widely used approach for event representation. Yet, there are multiple indications that semantic role paradigm is necessary but not sufficient to cover all elements of event structure. We conducted an analysis of…

计算与语言 · 计算机科学 2018-10-10 Aliaksandr Huminski , Hao Zhang

Video relation detection forms a new and challenging problem in computer vision, where subjects and objects need to be localized spatio-temporally and a predicate label needs to be assigned if and only if there is an interaction between the…

计算机视觉与模式识别 · 计算机科学 2021-10-26 Shuo Chen , Pascal Mettes , Cees G. M. Snoek

Referring Video Object Segmentation (RVOS) aims to segment out the object in a video referred by an expression. Current RVOS methods view referring expressions as unstructured sequences, neglecting their crucial semantic structure essential…

计算机视觉与模式识别 · 计算机科学 2025-08-15 Huihui Xu , Jiashi Lin , Haoyu Chen , Junjun He , Lei Zhu

The ability to reason about temporal and causal events from videos lies at the core of human intelligence. Most video reasoning benchmarks, however, focus on pattern recognition from complex visual and language input, instead of on causal…

计算机视觉与模式识别 · 计算机科学 2020-03-10 Kexin Yi , Chuang Gan , Yunzhu Li , Pushmeet Kohli , Jiajun Wu , Antonio Torralba , Joshua B. Tenenbaum

Visual representation learning is ubiquitous in various real-world applications, including visual comprehension, video understanding, multi-modal analysis, human-computer interaction, and urban computing. Due to the emergence of huge…

计算机视觉与模式识别 · 计算机科学 2023-03-23 Yang Liu , Yushen Wei , Hong Yan , Guanbin Li , Liang Lin

Recent large vision-language models have achieved strong performance on short- and medium-length video understanding, yet they remain inadequate for ultra-long or even infinite video reasoning, where models must preserve coherent memory…

人工智能 · 计算机科学 2026-05-08 Peizheng Yan , Yu Zhao , Liang Xie , Juntong Qi , Mingming Wang , Erwei Yin

As the intermediate-level representations bridging the two levels, structured representations of visual scenes, such as visual relationships between pairwise objects, have been shown to not only benefit compositional models in learning to…

计算机视觉与模式识别 · 计算机科学 2022-07-12 Meng-Jiun Chiou

Visual commonsense reasoning (VCR) is a challenging multi-modal task, which requires high-level cognition and commonsense reasoning ability about the real world. In recent years, large-scale pre-training approaches have been developed and…

计算机视觉与模式识别 · 计算机科学 2023-11-10 Cheng Yang , Rui Xu , Ye Guo , Peixiang Huang , Yiru Chen , Wenkui Ding , Zhongyuan Wang , Hong Zhou

Events in natural videos typically arise from spatio-temporal interactions between actors and objects and involve multiple co-occurring activities and object classes. To capture this rich visual and semantic context, we propose using two…

计算机视觉与模式识别 · 计算机科学 2020-10-01 Effrosyni Mavroudi , Benjamín Béjar Haro , René Vidal

Spatial relations are a basic part of human cognition. However, they are expressed in natural language in a variety of ways, and previous work has suggested that current vision-and-language models (VLMs) struggle to capture relational…

计算与语言 · 计算机科学 2023-03-23 Fangyu Liu , Guy Emerson , Nigel Collier

Understanding videos is an important research topic for multimodal learning. Leveraging large-scale datasets of web-crawled video-text pairs as weak supervision has become a pre-training paradigm for learning joint representations and…

计算机视觉与模式识别 · 计算机科学 2023-12-05 Gengyuan Zhang , Jinhe Bi , Jindong Gu , Yanyu Chen , Volker Tresp

Compositional spatio-temporal reasoning poses a significant challenge in the field of video question answering (VideoQA). Existing approaches struggle to establish effective symbolic reasoning structures, which are crucial for answering…

计算机视觉与模式识别 · 计算机科学 2024-04-08 Lili Liang , Guanglu Sun , Jin Qiu , Lizhong Zhang

Reasoning about real-life events is a unifying challenge in AI and NLP that has profound utility in a variety of domains, while fallacy in high-stake applications could be catastrophic. Able to work with diverse text in these domains, large…

计算与语言 · 计算机科学 2024-08-30 Li Zhang

After a decade of prosperity, the development of video understanding has reached a critical juncture, where the sole reliance on massive data and complex architectures is no longer a one-size-fits-all solution to all situations. The…

计算机视觉与模式识别 · 计算机科学 2025-03-18 Li Yicong

Causal and temporal reasoning about video dynamics is a challenging problem. While neuro-symbolic models that combine symbolic reasoning with neural-based perception and prediction have shown promise, they exhibit limitations, especially in…

人工智能 · 计算机科学 2025-06-13 Adam Ishay , Zhun Yang , Joohyung Lee , Ilgu Kang , Dongjae Lim
‹ 上一页 1 2 3 10 下一页 ›