相关论文: Continuous Perception Matters: Diagnosing Temporal…

Existing video understanding benchmarks often conflate knowledge-based and purely image-based questions, rather than clearly isolating a model's temporal reasoning ability, which is the key aspect that distinguishes video understanding from…

Combining LiDAR and Camera-view data has become a common approach for 3D Object Detection. However, previous approaches combine the two input streams at a point-level, throwing away semantic information derived from camera features. In this…

Continual post-training adapts a single text-to-image diffusion model to learn new tasks without incurring the cost of separate models, but naive post-training causes forgetting of pretrained knowledge and undermines zero-shot…

Topological mapping offers a compact and robust representation for navigation, but progress in the field is hindered by the lack of standardized evaluation metrics, datasets, and protocols. Existing systems are assessed using different…

Intrinsic image decomposition aims to estimate physically based rendering (PBR) parameters such as albedo, roughness, and metallicity from images. While recent methods achieve strong single-view predictions, applying them independently to…

Leveraging multiple sensors is crucial for robust semantic perception in autonomous driving, as each sensor type has complementary strengths and weaknesses. However, existing sensor fusion methods often treat sensors uniformly across all…

Fine-grained spatio-temporal understanding is essential for video reasoning and embodied AI. Yet, while Multimodal Large Language Models (MLLMs) master static semantics, their grasp of temporal dynamics remains brittle. We present…

Recent advancements in Large Vision-Language Models (LVLMs) have significantly enhanced their ability to integrate visual and linguistic information, achieving near-human proficiency in tasks like object recognition, captioning, and visual…

Video generation has witnessed significant advancements, yet evaluating these models remains a challenge. A comprehensive evaluation benchmark for video generation is indispensable for two reasons: 1) Existing metrics do not fully align…

Current perception models have achieved remarkable success by leveraging large-scale labeled datasets, but still face challenges in open-world environments with novel objects. To address this limitation, researchers introduce open-set…

The practicality of a video surveillance system is adversely limited by the amount of queries that can be placed on human resources and their vigilance in response. To transcend this limitation, a major effort under way is to include…

Multimodal large language models (MLLMs) have enabled a wide range of advanced vision-language applications, including fine-grained object recognition and contextual understanding. When querying specific regions or objects in an image,…

Although multimodal fusion has made significant progress, its advancement is severely hindered by the lack of adequate evaluation benchmarks. Current fusion methods are typically evaluated on a small selection of public datasets, a limited…

Concept Bottleneck Models (CBMs) have garnered much attention for their ability to elucidate the prediction process through a human-understandable concept layer. However, most previous studies focused on static scenarios where the data and…

While recent camera-only 3D detection methods leverage multiple timesteps, the limited history they use significantly hampers the extent to which temporal fusion can improve object perception. Observing that existing works' fusion of…

Collaborative perception (CP) is a promising method for safe connected and autonomous driving, which enables multiple vehicles to share sensing information to enhance perception performance. However, compared with single-vehicle perception,…

Diffusion models excel in noise-to-data generation tasks, providing a mapping from a Gaussian distribution to a more complex data distribution. However they struggle to model translations between complex distributions, limiting their…

Applying image processing algorithms independently to each video frame often leads to temporal inconsistency in the resulting video. To address this issue, we present a novel and general approach for blind video temporal consistency. Our…

Multimodal Large Language Models (MLLMs) have achieved remarkable success in open-vocabulary perceptual tasks, yet their ability to solve complex cognitive problems remains limited, especially when visual details are abstract and require…

The performance of autonomous systems heavily relies on their ability to generate a robust representation of the environment. Deep neural networks have greatly improved vision-based perception systems but still fail in challenging…