Complement
发表于 2025-4-1 02:08:16
http://reply.papertrans.cn/25/2424/242355/242355_61.png
两栖动物
发表于 2025-4-1 07:55:37
Jennifer Renoux,Uwe Köckemann,Amy Loutfi) Cross-Model feature Mixup, which learns similarities between embeddings obtained from current and old models of the mixed sample and the original images, facilitating cross-task class contrast learning and old knowledge retrieval. We evaluate the effectiveness of CroMo-Mixup to improve both Task-I
Crepitus
发表于 2025-4-1 12:42:43
http://reply.papertrans.cn/25/2424/242355/242355_63.png
不理会
发表于 2025-4-1 17:00:34
http://reply.papertrans.cn/25/2424/242355/242355_64.png
巨头
发表于 2025-4-1 22:33:16
,SAVE: Protagonist Diversification with ,tructure ,gnostic ,ideo ,diting, Accordingly, tasks such as modifying the object or changing the style in a video have been possible. However, previous works usually work well on trivial and consistent shapes, and easily collapse on a difficult target that has a largely different body shape from the original one. In this paper, we
embolus
发表于 2025-4-1 23:46:59
,: Long-Form Video Understanding with Large Language Model as Agent,sequences. Motivated by the human cognitive process for long-form video understanding, we emphasize interactive reasoning and planning over the ability to process lengthy visual inputs. We introduce a novel agent-based system, ., that employs a large language model as a central agent to iteratively
Panacea
发表于 2025-4-2 06:13:17
,Meta-optimized Angular Margin Contrastive Framework for Video-Language Representation Learning,ta typically do not align perfectly with each other, which might lead to video-language representations that do not accurately reflect cross-modal semantics. Moreover, previous data also possess an uneven distribution of concepts, thereby hampering the downstream performance across unpopular subject
不能逃避
发表于 2025-4-2 09:18:56
Source-Free Domain-Invariant Performance Prediction,data distributions. Most existing performance prediction methods heavily rely on the source data in their estimation process, limiting their applicability in a more realistic setting where only the trained model is accessible. The few methods that do not require source data exhibit considerably infe
痛苦一生
发表于 2025-4-2 14:06:15
,Improving Robustness to Model Inversion Attacks via Sparse Coding Architectures,tedly querying the network. In this work, we develop a novel network architecture that leverages sparse-coding layers to obtain superior robustness to this class of attacks. Three decades of computer science research has studied sparse coding in the context of image denoising, object recognition, an
chastise
发表于 2025-4-2 15:48:45
,Constructing Concept-Based Models to Mitigate Spurious Correlations with Minimal Human Effort,n provide a principled way of disclosing and guiding model behaviors through human-understandable concepts, albeit at a high cost of human efforts in data annotation. In this paper, we leverage a synergy of multiple foundation models to construct CBMs with nearly no human effort. We discover undesir