Add causal person fusion and MuVAP stage-3 baselines

2026-09-10 06:54:22 +08:00
parent 0534c9d3d0
commit d426b4740a
225 changed files with 27716 additions and 119 deletions
@@ -0,0 +1,32 @@
+model: 'MambaA'
+data_name: 'YTConv_ANTICIPATION'
+data_info_name: 'shard_0'
+task: 'ANTICIPATION'
+loss: 'ANTICIPATION' # NONUNIFORM, originally
+metric: 'AP' # AP or cAP
+optimizer: 'AdamW'
+device: 'cuda'
+feature_pretrained: 'resnet50'
+root_path: './data/YTConv/shard_0'
+rgb_type: 'rgb_kinetics_resnet50'
+flow_type: 'audio_wav2vec2' # or 'none'?
+annotation_type: 'target_perframe/case1'
+video_list_path: 'data_info/YTConv_info.json'
+output_path: './output_cfg'
+window_size: 128
+batch_size: 32 
+test_batch_size: 1 
+# loss_offset: 4 # loss weight a_t when L - {loss_offset} <= t <= L
+num_epoch: 30
+lr: 0.0001
+weight_decay: 0.05
+num_workers: 4
+dropout: 0.20
+num_classes: 2 # for YTConv pretraining, there is no 
+embedding_dim: 2048
+hidden_dim: 1024
+num_layers: 1
+stride: 4
+anticipation_length: 10
+actionness: False
+ignore_index: -100
@@ -0,0 +1,32 @@
+model: 'MiniROADA'
+data_name: 'YTConv_ANTICIPATION'
+data_info_name: 'shard_0'
+task: 'ANTICIPATION'
+loss: 'ANTICIPATION' # NONUNIFORM, originally
+metric: 'AP' # AP or cAP
+optimizer: 'AdamW'
+device: 'cuda'
+feature_pretrained: 'resnet50'
+root_path: './data/YTConv/shard_0'
+rgb_type: 'rgb_kinetics_resnet50'
+flow_type: 'audio_wav2vec2'
+annotation_type: 'target_perframe'
+video_list_path: 'data_info/YTConv_info.json'
+output_path: './output_cfg'
+window_size: 128
+batch_size: 64 
+test_batch_size: 1 
+# loss_offset: 4 # loss weight a_t when L - {loss_offset} <= t <= L
+num_epoch: 30
+lr: 0.0001
+weight_decay: 0.05
+num_workers: 4
+dropout: 0.20
+num_classes: 2 # for pretraining, there is no target speaker
+embedding_dim: 2048
+hidden_dim: 1024
+num_layers: 1
+stride: 4
+anticipation_length: 10
+actionness: False
+ignore_index: -100