Related papers: Soft-Landing Strategy for Alleviating the Task Dis…

With the rise of Visual and Language Pretraining (VLP), an increasing number of downstream tasks are adopting the paradigm of pretraining followed by fine-tuning. Although this paradigm has demonstrated potential in various multimodal…

Large language models (LLMs) demonstrate strong task-specific capabilities through fine-tuning, but merging multiple fine-tuned models often leads to degraded performance due to overlapping instruction-following components. Task Arithmetic…

Multitask learning (MTL) has become prominent for its ability to predict multiple tasks jointly, achieving better per-task performance with fewer parameters than single-task learning. Recently, decoder-focused architectures have…

Parameter-efficient fine-tuning (PEFT) has been widely employed for domain adaptation, with LoRA being one of the most prominent methods due to its simplicity and effectiveness. However, in multi-task learning (MTL) scenarios, LoRA tends to…

Temporal action localization (TAL), which involves recognizing and locating action instances, is a challenging task in video understanding. Most existing approaches directly predict action classes and regress offsets to boundaries, while…

Recently, temporal action localization (TAL), i.e., finding specific action segments in untrimmed videos, has attracted increasing attentions of the computer vision community. State-of-the-art solutions for TAL involves evaluating the…

Weakly supervised temporal action localization (WTAL) aims to localize actions in untrimmed videos with only weak supervision information (e.g. video-level labels). Most existing models handle all input videos with a fixed temporal scale.…

The task of language-guided video temporal grounding is to localize the particular video clip corresponding to a query sentence in an untrimmed video. Though progress has been made continuously in this field, some issues still need to be…

Transfer learning is widely used in deep neural network models when there are few labeled examples available. The common approach is to take a pre-trained network in a similar task and finetune the model parameters. This is usually done…

Procedural activity videos often exhibit a long-tailed action distribution due to varying action frequencies and durations. However, state-of-the-art temporal action segmentation methods overlook the long tail and fail to recognize tail…

Intermediate training of pre-trained transformer-based language models on domain-specific data leads to substantial gains for downstream tasks. To increase efficiency and prevent catastrophic forgetting alleviated from full domain-adaptive…

Vision-language models (VLMs) such as CLIP demonstrate strong generalization in zero-shot classification but remain highly vulnerable to adversarial perturbations. Existing methods primarily focus on adversarial fine-tuning or prompt…

Weakly-supervised temporal action localization aims to locate action regions and identify action categories in untrimmed videos simultaneously by taking only video-level labels as the supervision. Pseudo label generation is a promising…

Once-for-All (OFA) training enables a single super-net to generate multiple sub-nets tailored to diverse deployment scenarios, supporting flexible trade-offs among accuracy, robustness, and model-size without retraining. However, as the…

Temporal Action Localization (TAL) has experienced remarkable success under the supervised learning paradigm. However, existing TAL methods are rooted in the closed set assumption, which cannot handle the inevitable unknown actions in…

Temporal Action Localization (TAL) is a critical task in video analysis, identifying precise start and end times of actions. Existing methods like CNNs, RNNs, GCNs, and Transformers have limitations in capturing long-range dependencies and…

Learning fine-grained interplay between vision and language allows to a more accurate understanding for VisionLanguage tasks. However, it remains challenging to extract key image regions according to the texts for semantic alignments. Most…

Weakly-supervised temporal action localization (WTAL) aims to recognize and localize action instances with only video-level labels. Despite the significant progress, existing methods suffer from severe performance degradation when…

Temporal action segmentation (TAS) aims to classify and locate actions in the long untrimmed action sequence. With the success of deep learning, many deep models for action segmentation have emerged. However, few-shot TAS is still a…

Test-time adaptation (TTA) has gained increasing popularity due to its efficacy in addressing ``distribution shift'' issue while simultaneously protecting data privacy. However, most prior methods assume that a paired source domain model…