相关论文: NAVERO: Unlocking Fine-Grained Semantics for Video…
With advances in image recognition technology based on deep learning, automatic video analysis by Artificial Intelligence is becoming more widespread. As the amount of video used for image recognition increases, efficient compression…
Vision-language models such as CLIP have shown impressive capabilities in encoding texts and images into aligned embeddings, enabling the retrieval of multimodal data in a shared embedding space. However, these embedding-based models still…
Recent advances in video large language models (VideoLLMs) call for new evaluation protocols and benchmarks for complex temporal reasoning in video-language understanding. Inspired by the needle in a haystack test widely used by LLMs, we…
Learning interpretable representations of visual data is an important challenge, to make machines' decisions understandable to humans and to improve generalisation outside of the training distribution. To this end, we propose a deep…
Composed video retrieval (CoVR) is a challenging problem in computer vision which has recently highlighted the integration of modification text with visual queries for more sophisticated video search in large databases. Existing works…
Video compression is indispensable to most video analysis systems. Despite saving transportation bandwidth, it also deteriorates downstream video understanding tasks, especially at low-bitrate settings. To systematically investigate this…
This paper investigates the problem of zero-shot action recognition, in the setting where no training videos with seen actions are available. For this challenging scenario, the current leading approach is to transfer knowledge from the…
We introduce VidLPRO, a novel video-language (VL) pre-training framework designed specifically for robotic and laparoscopic surgery. While existing surgical VL models primarily rely on contrastive learning, we propose a more comprehensive…
Visual-Language-Action (VLA) models report impressive success rates on robotic manipulation benchmarks, yet these results may mask fundamental weaknesses in robustness. We perform a systematic vulnerability analysis by introducing…
Recent work has empirically shown that Vision-Language Models (VLMs) struggle to fully understand the compositional properties of the human language, usually modeling an image caption as a "bag of words". As a result, they perform poorly on…
The advent of large Vision-Language Models (VLMs) has significantly advanced multimodal understanding, enabling more sophisticated and accurate integration of visual and textual information across various tasks, including image and video…
Action recognition is an important problem in multimedia understanding. This paper addresses this problem by building an expressive compositional action model. We model one action instance in the video with an ensemble of spatio-temporal…
Video language continual learning involves continuously adapting to information from video and text inputs, enhancing a model's ability to handle new tasks while retaining prior knowledge. This field is a relatively under-explored area, and…
While recent text-to-video models excel at generating diverse scenes, they struggle with precise motion control, particularly for complex, multi-subject motions. Although methods for single-motion customization have been developed to…
Contrastive learning has been widely used to train transformer-based vision-language models for video-text alignment and multi-modal representation learning. This paper presents a new algorithm called Token-Aware Cascade contrastive…
What makes good representations for video understanding, such as anticipating future activities, or answering video-conditioned questions? While earlier approaches focus on end-to-end learning directly from video pixels, we propose to…
Solving complex, temporally-extended tasks is a long-standing problem in reinforcement learning (RL). We hypothesize that one critical element of solving such problems is the notion of compositionality. With the ability to learn concepts…
The explosive growth of video streaming presents challenges in achieving high accuracy and low training costs for video-language retrieval. However, existing methods rely on large-scale pre-training to improve video retrieval performance,…
Previous Vision-Language-Action models face critical limitations in navigation: scarce, diverse data from labor-intensive collection and static representations that fail to capture temporal dynamics and physical laws. We propose NavDreamer,…
LIBERO has emerged as a widely adopted benchmark for evaluating Vision-Language-Action (VLA) models; however, its current training and evaluation settings are problematic, often leading to inflated performance estimates and preventing fair…