English
Related papers

Related papers: Rethinking Position Embedding as a Context Control…

200 papers

In this paper, we address the problem of referring expression comprehension in videos, which is challenging due to complex expression and scene dynamics. Unlike previous methods which solve the problem in multiple stages (i.e., tracking,…

Computer Vision and Pattern Recognition · Computer Science 2021-03-24 Sijie Song , Xudong Lin , Jiaying Liu , Zongming Guo , Shih-Fu Chang

Imitation learning enables robots to learn new tasks from human examples. One fundamental limitation while learning from humans is causal confusion. Causal confusion occurs when the robot's observations include both task-relevant and…

Robotics · Computer Science 2025-03-04 Robert Ramirez Sanchez , Heramb Nemlekar , Shahabedin Sagheb , Cara M. Nunez , Dylan P. Losey

Automatic generation of high-quality commit messages for code commits can substantially facilitate software developers' works and coordination. However, the semantic gap between source code and natural language poses a major challenge for…

Computation and Language · Computer Science 2021-06-22 Lun Yiu Nie , Cuiyun Gao , Zhicong Zhong , Wai Lam , Yang Liu , Zenglin Xu

Generating temporally coherent, long-duration videos with precise control over subject identity and movement remains a fundamental challenge for contemporary diffusion-based models, which often suffer from identity drift and are limited to…

Computer Vision and Pattern Recognition · Computer Science 2026-04-13 Jingxuan He , Busheng Su , Finn Wong

Many existing motion prediction approaches rely on symbolic perception outputs to generate agent trajectories, such as bounding boxes, road graph information and traffic lights. This symbolic representation is a high-level abstraction of…

Computer Vision and Pattern Recognition · Computer Science 2024-05-01 Norman Mu , Jingwei Ji , Zhenpei Yang , Nate Harada , Haotian Tang , Kan Chen , Charles R. Qi , Runzhou Ge , Kratarth Goel , Zoey Yang , Scott Ettinger , Rami Al-Rfou , Dragomir Anguelov , Yin Zhou

Video generation models have made significant progress in generating realistic content, enabling applications in simulation, gaming, and film making. However, current generated videos still contain visual artifacts arising from 3D…

Computer Vision and Pattern Recognition · Computer Science 2025-11-25 Duolikun Danier , Ge Gao , Steven McDonagh , Changjian Li , Hakan Bilen , Oisin Mac Aodha

The field of text-to-image (T2I) generation has made significant progress in recent years, largely driven by advancements in diffusion models. Linguistic control enables effective content creation, but struggles with fine-grained control…

Computer Vision and Pattern Recognition · Computer Science 2024-07-19 Yanan Sun , Yanchen Liu , Yinhao Tang , Wenjie Pei , Kai Chen

We propose to learn word embeddings from visual co-occurrences. Two words co-occur visually if both words apply to the same image or image region. Specifically, we extract four types of visual co-occurrences between object and attribute…

Computer Vision and Pattern Recognition · Computer Science 2019-08-23 Tanmay Gupta , Alexander Schwing , Derek Hoiem

Interactive video generation has significant potential for scene simulation and video creation. However, existing methods often struggle with maintaining scene consistency during long video generation under dynamic camera control due to…

Computer Vision and Pattern Recognition · Computer Science 2026-03-30 Xinhang Gao , Junlin Guan , Shuhan Luo , Wenzhuo Li , Guanghuan Tan , Jiacheng Wang

We address the problem of multi-object 3D pose control in image diffusion models. Instead of conditioning on a sequence of text tokens, we propose to use a set of per-object representations, Neural Assets, to control the 3D pose of…

Computer Vision and Pattern Recognition · Computer Science 2024-10-30 Ziyi Wu , Yulia Rubanova , Rishabh Kabra , Drew A. Hudson , Igor Gilitschenski , Yusuf Aytar , Sjoerd van Steenkiste , Kelsey R. Allen , Thomas Kipf

We present models for embedding words in the context of surrounding words. Such models, which we refer to as token embeddings, represent the characteristics of a word that are specific to a given context, such as word sense, syntactic…

Computation and Language · Computer Science 2017-06-13 Lifu Tu , Kevin Gimpel , Karen Livescu

The ability to integrate context, including perceptual and temporal cues, plays a pivotal role in grounding the meaning of a linguistic utterance. In order to measure to what extent current vision-and-language models master this ability, we…

Computer Vision and Pattern Recognition · Computer Science 2022-11-21 Benno Krojer , Vaibhav Adlakha , Vibhav Vineet , Yash Goyal , Edoardo Ponti , Siva Reddy

Most Neural Video Codecs (NVCs) only employ temporal references to generate temporal-only contexts and latent prior. These temporal-only NVCs fail to handle large motions or emerging objects due to limited contexts and misaligned latent…

Image and Video Processing · Electrical Eng. & Systems 2025-05-09 Yifan Bian , Chuanbo Tang , Li Li , Dong Liu

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.…

Computer Vision and Pattern Recognition · Computer Science 2020-11-20 Hassan Akbari , Hamid Palangi , Jianwei Yang , Sudha Rao , Asli Celikyilmaz , Roland Fernandez , Paul Smolensky , Jianfeng Gao , Shih-Fu Chang

Diffusion models are a new class of generative models, and have dramatically promoted image generation with unprecedented quality and diversity. Existing diffusion models mainly try to reconstruct input image from a corrupted one with a…

Computer Vision and Pattern Recognition · Computer Science 2024-06-05 Ling Yang , Jingwei Liu , Shenda Hong , Zhilong Zhang , Zhilin Huang , Zheming Cai , Wentao Zhang , Bin Cui

Learning visual representations from observing actions to benefit robot visuo-motor policy generation is a promising direction that closely resembles human cognitive function and perception. Motivated by this, and further inspired by…

Training general robotic policies from heterogeneous data for different tasks is a significant challenge. Existing robotic datasets vary in different modalities such as color, depth, tactile, and proprioceptive information, and collected in…

Robotics · Computer Science 2024-12-03 Lirui Wang , Jialiang Zhao , Yilun Du , Edward H. Adelson , Russ Tedrake

Video semantic search in densely crowded scenes remains a challenging task due to visual encoders tendency to prioritize salient foreground regions while neglecting contextually important, background areas. We propose an Inverse Attention…

Computer Vision and Pattern Recognition · Computer Science 2026-05-08 Faisal Aljehrai , Mohammed A. Alkhrashi , Alreem Almuhrij , Sarah Abuhimed , Noorh Aldossary , Abdullah Aldwyish , Raied Aljadaany , Huda Alamri , Muhammad Kamran J Khan

In text-to-image diffusion models, the cross-attention map of each text token indicates the specific image regions attended. Comparing these maps of syntactically related tokens provides insights into how well the generated image reflects…

Computer Vision and Pattern Recognition · Computer Science 2024-11-26 Jeeyung Kim , Erfan Esmaeili , Qiang Qiu

This paper addresses the challenging task of video captioning which aims to generate descriptions for video data. Recently, the attention-based encoder-decoder structures have been widely used in video captioning. In existing literature,…

Machine Learning · Computer Science 2019-11-04 Tao Jin , Siyu Huang , Yingming Li , Zhongfei Zhang
‹ Prev 1 4 5 6 7 8 10 Next ›